Vipin Kumar

Hector Zenil, Jesper Tegnér, Felipe S. Abrahão et al. · cambridge

Recent advances in machine learning and AI, including Generative AI and LLMs, are disrupting technological innovation, product development, and society as a whole. AI's contribution to technology can come from multiple approaches that require access to large training data sets and clear performance evaluation criteria, ranging from pattern recognition and classification to generative models. Yet, AI has contributed less to fundamental science in part because large data sets of high-quality data for scientific practice and model discovery are more difficult to access. Generative AI, in general, and Large Language Models in particular, may represent an opportunity to augment and accelerate the scientific discovery of fundamental deep science with quantitative models. Here we explore and investigate aspects of an AI-driven, automated, closed-loop approach to scientific discovery, including self-driven hypothesis generation and open-ended autonomous exploration of the hypothesis space. Integrating AI-driven automation into the practice of science would mitigate current problems, including the replication of findings, systematic production of data, and ultimately democratisation of the scientific process. Realising these possibilities requires a vision for augmented AI coupled with a diversity of AI approaches able to deal with fundamental aspects of causality analysis and model discovery while enabling unbiased search across the space of putative explanations. These advances hold the promise to unleash AI's potential for searching and discovering the fundamental structure of our world beyond what human scientists have been able to achieve. Such a vision would push the boundaries of new fundamental science rather than automatize current workflows and instead open doors for technological innovation to tackle some of the greatest challenges facing humanity today.

Lily Xu, Esther Rolf, Sara Beery et al. · mit

In this white paper, we synthesize key points made during presentations and discussions from the AI-Assisted Decision Making for Conservation workshop, hosted by the Center for Research on Computation and Society at Harvard University on October 20-21, 2022. We identify key open research questions in resource allocation, planning, and interventions for biodiversity conservation, highlighting conservation challenges that not only require AI solutions, but also require novel methodological advances. In addition to providing a summary of the workshop talks and discussions, we hope this document serves as a call-to-action to orient the expansion of algorithmic decision-making approaches to prioritize real-world conservation challenges, through collaborative efforts of ecologists, conservation decision-makers, and AI researchers.

Longbing Cao, Hui Chen, Xuhui Fan et al.

Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. However, the robustness and capabilities of existing FL methods are challenged by limited and dynamic data and conditions, complexities including heterogeneities and uncertainties, and analytical explainability. Bayesian federated learning (BFL) has emerged as a promising approach to address these issues. This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives. We categorize and discuss client- and server-side and FL-based BFL methods and their pros and cons. The limitations of the existing BFL methods and the future directions of BFL research further address the intricate requirements of real-life FL applications.

Leikun Yin, Rahul Ghosh, Chenxi Lin et al.

Cashews are grown by over 3 million smallholders in more than 40 countries worldwide as a principal source of income. As the third largest cashew producer in Africa, Benin has nearly 200,000 smallholder cashew growers contributing 15% of the country's national export earnings. However, a lack of information on where and how cashew trees grow across the country hinders decision-making that could support increased cashew production and poverty alleviation. By leveraging 2.4-m Planet Basemaps and 0.5-m aerial imagery, newly developed deep learning algorithms, and large-scale ground truth datasets, we successfully produced the first national map of cashew in Benin and characterized the expansion of cashew plantations between 2015 and 2021. In particular, we developed a SpatioTemporal Classification with Attention (STCA) model to map the distribution of cashew plantations, which can fully capture texture information from discriminative time steps during a growing season. We further developed a Clustering Augmented Self-supervised Temporal Classification (CASTC) model to distinguish high-density versus low-density cashew plantations by automatic feature extraction and optimized clustering. Results show that the STCA model has an overall accuracy over 85% and the CASTC model achieved an overall accuracy of 76%. We found that the cashew area in Benin almost doubled from 2015 to 2021 with 60% of new plantation development coming from cropland or fallow land, while encroachment of cashew plantations into protected areas has increased by 55%. Only half of cashew plantations were high-density in 2021, suggesting high potential for intensification. Our study illustrates the power of combining high-resolution remote sensing imagery and state-of-the-art deep learning algorithms to better understand tree crops in the heterogeneous smallholder landscape.

Shaoming Xu, Ankush Khandelwal, Xiang Li et al.

In many environmental applications, recurrent neural networks (RNNs) are often used to model physical variables with long temporal dependencies. However, due to mini-batch training, temporal relationships between training segments within the batch (intra-batch) as well as between batches (inter-batch) are not considered, which can lead to limited performance. Stateful RNNs aim to address this issue by passing hidden states between batches. Since Stateful RNNs ignore intra-batch temporal dependency, there exists a trade-off between training stability and capturing temporal dependency. In this paper, we provide a quantitative comparison of different Stateful RNN modeling strategies, and propose two strategies to enforce both intra- and inter-batch temporal dependency. First, we extend Stateful RNNs by defining a batch as a temporally ordered set of training segments, which enables intra-batch sharing of temporal information. While this approach significantly improves the performance, it leads to much larger training times due to highly sequential training. To address this issue, we further propose a new strategy which augments a training segment with an initial value of the target variable from the timestep right before the starting of the training segment. In other words, we provide an initial value of the target variable as additional input so that the network can focus on learning changes relative to that initial value. By using this strategy, samples can be passed in any order (mini-batch training) which significantly reduces the training time while maintaining the performance. In demonstrating our approach in hydrological modeling, we observe that the most significant gains in predictive accuracy occur when these methods are applied to state variables whose values change more slowly, such as soil water and snowpack, rather than continuously moving flux variables such as streamflow.

Reyhaneh Rahimi, Praveen Ravirathinam, Ardeshir Ebtehaj et al.

This paper presents a deep learning architecture for nowcasting of precipitation almost globally every 30 min with a 4-hour lead time. The architecture fuses a U-Net and a convolutional long short-term memory (LSTM) neural network and is trained using data from the Integrated MultisatellitE Retrievals for GPM (IMERG) and a few key precipitation drivers from the Global Forecast System (GFS). The impacts of different training loss functions, including the mean-squared error (regression) and the focal-loss (classification), on the quality of precipitation nowcasts are studied. The results indicate that the regression network performs well in capturing light precipitation (below 1.6 mm/hr), but the classification network can outperform the regression network for nowcasting of precipitation extremes (>8 mm/hr), in terms of the critical success index (CSI).. Using the Wasserstein distance, it is shown that the predicted precipitation by the classification network has a closer class probability distribution to the IMERG than the regression network. It is uncovered that the inclusion of the physical variables can improve precipitation nowcasting, especially at longer lead times in both networks. Taking IMERG as a relative reference, a multi-scale analysis in terms of fractions skill score (FSS), shows that the nowcasting machine remains skillful (FSS > 0.5) at the resolution of 10 km compared to 50 km for GFS. For precipitation rates greater than 4~mm/hr, only the classification network remains FSS-skillful on scales greater than 50 km within a 2-hour lead time.

Jared D. Willard, Charuleka Varadharajan, Xiaowei Jia et al.

Prediction of dynamic environmental variables in unmonitored sites remains a long-standing challenge for water resources science. The majority of the world's freshwater resources have inadequate monitoring of critical environmental variables needed for management. Yet, the need to have widespread predictions of hydrological variables such as river flow and water quality has become increasingly urgent due to climate and land use change over the past decades, and their associated impacts on water resources. Modern machine learning methods increasingly outperform their process-based and empirical model counterparts for hydrologic time series prediction with their ability to extract information from large, diverse data sets. We review relevant state-of-the art applications of machine learning for streamflow, water quality, and other water resources prediction and discuss opportunities to improve the use of machine learning with emerging methods for incorporating watershed characteristics into deep learning models, transfer learning, and incorporating process knowledge into machine learning models. The analysis here suggests most prior efforts have been focused on deep learning learning frameworks built on many sites for predictions at daily time scales in the United States, but that comparisons between different classes of machine learning methods are few and inadequate. We identify several open questions for time series predictions in unmonitored sites that include incorporating dynamic inputs and site characteristics, mechanistic understanding and spatial context, and explainable AI techniques in modern machine learning frameworks.

Divya Kumawat, Ardeshir Ebtehaj, Xiaolan Xu et al.

Estimating the landscape and soil freeze-thaw (FT) dynamics in the Northern Hemisphere is crucial for understanding permafrost response to global warming and changes in regional and global carbon budgets. A new framework is presented for surface FT-cycle retrievals using L-band microwave radiometry based on a deep convolutional autoencoder neural network. This framework defines the landscape FT-cycle retrieval as a time series anomaly detection problem considering the frozen states as normal and thawed states as anomalies. The autoencoder retrieves the FT-cycle probabilistically through supervised reconstruction of the brightness temperature (TB) time series using a contrastive loss function that minimizes (maximizes) the reconstruction error for the peak winter (summer). Using the data provided by the Soil Moisture Active Passive (SMAP) satellite, it is demonstrated that the framework learns to isolate the landscape FT states over different land surface types with varying complexities related to the radiometric characteristics of snow cover, lake-ice phenology, and vegetation canopy. The consistency of the retrievals is evaluated over Alaska, against in situ ground-based observations, showing reduced uncertainties compared to the traditional methods that use thresholding of the normalized polarization ratio.

Kshitij Tayal, Arvind Renganathan, Rahul Ghosh et al.

Accurate long-term predictions are the foundations for many machine learning applications and decision-making processes. However, building accurate long-term prediction models remains challenging due to the limitations of existing temporal models like recurrent neural networks (RNNs), as they capture only the statistical connections in the training data and may fail to learn the underlying dynamics of the target system. To tackle this challenge, we propose a novel machine learning model based on Koopman operator theory, which we call Koopman Invertible Autoencoders (KIA), that captures the inherent characteristic of the system by modeling both forward and backward dynamics in the infinite-dimensional Hilbert space. This enables us to efficiently learn low-dimensional representations, resulting in more accurate predictions of long-term system behavior. Moreover, our method's invertibility design guarantees reversibility and consistency in both forward and inverse operations. We illustrate the utility of KIA on pendulum and climate datasets, demonstrating 300% improvements in long-term prediction capability for pendulum while maintaining robustness against noise. Additionally, our method excels in long-term climate prediction, further validating our method's effectiveness.

Rahul Ghosh, Haoyu Yang, Ankush Khandelwal et al.

Personalized prediction of responses for individual entities caused by external drivers is vital across many disciplines. Recent machine learning (ML) advances have led to new state-of-the-art response prediction models. Models built at a population level often lead to sub-optimal performance in many personalized prediction settings due to heterogeneity in data across entities (tasks). In personalized prediction, the goal is to incorporate inherent characteristics of different entities to improve prediction performance. In this survey, we focus on the recent developments in the ML community for such entity-aware modeling approaches. ML algorithms often modulate the network using these entity characteristics when they are readily available. However, these entity characteristics are not readily available in many real-world scenarios, and different ML methods have been proposed to infer these characteristics from the data. In this survey, we have organized the current literature on entity-aware modeling based on the availability of these characteristics as well as the amount of training data. We highlight how recent innovations in other disciplines, such as uncertainty quantification, fairness, and knowledge-guided machine learning, can improve entity-aware modeling.

Rahul Ghosh, Arvind Renganathan, Zac McEachran et al.

We present a framework for modeling multi-scale processes, and study its performance in the context of streamflow forecasting in hydrology. Specifically, we propose a novel hierarchical recurrent neural architecture that factorizes the system dynamics at multiple temporal scales and captures their interactions. This framework consists of an inverse and a forward model. The inverse model is used to empirically resolve the system's temporal modes from data (physical model simulations, observed data, or a combination of them from the past), and these states are then used in the forward model to predict streamflow. Experiments on several catchments from the National Weather Service North Central River Forecast Center show that FHNN outperforms standard baselines, including physics-based models and transformer-based approaches. The model demonstrates particular effectiveness in catchments with low runoff ratios and colder climates. We further validate FHNN on the CAMELS (Catchment Attributes and MEteorology for Large-sample Studies), which is a widely used continental-scale hydrology benchmark dataset, confirming consistent performance improvements for 1-7 day streamflow forecasts across diverse hydrological conditions. Additionally, we show that FHNN can maintain accuracy even with limited training data through effective pre-training strategies and training global models.

Somya Sharma Chatterjee, Kelly Lindsay, Neel Chatterjee et al.

In recent years, the increasing threat of devastating wildfires has underscored the need for effective prescribed fire management. Process-based computer simulations have traditionally been employed to plan prescribed fires for wildfire prevention. However, even simplified process models like QUIC-Fire are too compute-intensive to be used for real-time decision-making, especially when weather conditions change rapidly. Traditional ML methods used for fire modeling offer computational speedup but struggle with physically inconsistent predictions, biased predictions due to class imbalance, biased estimates for fire spread metrics (e.g., burned area, rate of spread), and generalizability in out-of-distribution wind conditions. This paper introduces a novel machine learning (ML) framework that enables rapid emulation of prescribed fires while addressing these concerns. By incorporating domain knowledge, the proposed method helps reduce physical inconsistencies in fuel density estimates in data-scarce scenarios. To overcome the majority class bias in predictions, we leverage pre-existing source domain data to augment training data and learn the spread of fire more effectively. Finally, we overcome the problem of biased estimation of fire spread metrics by incorporating a hierarchical modeling structure to capture the interdependence in fuel density and burned area. Notably, improvement in fire metric (e.g., burned area) estimates offered by our framework makes it useful for fire managers, who often rely on these fire metric estimates to make decisions about prescribed burn management. Furthermore, our framework exhibits better generalization capabilities than the other ML-based fire modeling methods across diverse wind conditions and ignition patterns.

Somya Sharma, Rahul Ghosh, Arvind Renganathan et al.

The astounding success of these methods has made it imperative to obtain more explainable and trustworthy estimates from these models. In hydrology, basin characteristics can be noisy or missing, impacting streamflow prediction. For solving inverse problems in such applications, ensuring explainability is pivotal for tackling issues relating to data bias and large search space. We propose a probabilistic inverse model framework that can reconstruct robust hydrology basin characteristics from dynamic input weather driver and streamflow response data. We address two aspects of building more explainable inverse models, uncertainty estimation and robustness. This can help improve the trust of water managers, handling of noisy data and reduce costs. We propose uncertainty based learning method that offers 6\% improvement in $R^2$ for streamflow prediction (forward modeling) from inverse model inferred basin characteristic estimates, 17\% reduction in uncertainty (40\% in presence of noise) and 4\% higher coverage rate for basin characteristics.

Jia Li, Xiang Li, Xiaowei Jia et al.

Causal DAGs(Directed Acyclic Graphs) are usually considered in a 2D plane. Edges indicate causal effects' directions and imply their corresponding time-passings. Due to the natural restriction of statistical models, effect estimation is usually approximated by averaging the individuals' correlations, i.e., observational changes over a specific time. However, in the context of Machine Learning on large-scale questions with complex DAGs, such slight biases can snowball to distort global models - More importantly, it has practically impeded the development of AI, for instance, the weak generalizability of causal models. In this paper, we redefine causal DAG as \emph{do-DAG}, in which variables' values are no longer time-stamp-dependent, and timelines can be seen as axes. By geometric explanation of multi-dimensional do-DAG, we identify the \emph{Causal Representation Bias} and its necessary factors, differentiated from common confounding biases. Accordingly, a DL(Deep Learning)-based framework will be proposed as the general solution, along with a realization method and experiments to verify its feasibility.

Praveen Ravirathinam, Rahul Ghosh, Ke Wang et al.

Creating separable representations via representation learning and clustering is critical in analyzing large unstructured datasets with only a few labels. Separable representations can lead to supervised models with better classification capabilities and additionally aid in generating new labeled samples. Most unsupervised and semisupervised methods to analyze large datasets do not leverage the existing small amounts of labels to get better representations. In this paper, we propose a spatiotemporal clustering paradigm that uses spatial and temporal features combined with a constrained loss to produce separable representations. We show the working of this method on the newly published dataset ReaLSAT, a dataset of surface water dynamics for over 680,000 lakes across the world, making it an essential dataset in terms of ecology and sustainability. Using this large unlabelled dataset, we first show how a spatiotemporal representation is better compared to just spatial or temporal representation. We then show how we can learn even better representation using a constrained loss with few labels. We conclude by showing how our method, using few labels, can pick out new labeled samples from the unlabeled data, which can be used to augment supervised methods leading to better classification.

Praveen Ravirathinam, Ajitesh Parthasarathy, Ankush Khandelwal et al.

Self-supervised learning has emerged as a powerful paradigm for pretraining foundation models using large-scale data. Existing pretraining approaches predominantly rely on masked reconstruction or next-token prediction strategies, demonstrating strong performance across various downstream tasks, including geoscience applications. However, these approaches do not fully capture the knowledge of causal interplay between different geospatial and environmental variables. To address this limitation, we propose Knowledge Guided Variable-Step Forecasting (KG-VSF), a novel pretraining task that models forecasting as a conditional generation task, where driver variables (e.g., weather) inform the prediction of response variables (e.g., satellite imagery). We demonstrate that pretraining in such a fashion leads to strong embeddings which give enhanced performance when finetuned on downstream tasks where capturing this causality matters such as pixel wise crop type mapping, soil moisture estimation and forecasting, missing image prediction, and future image forecasting when compared to finetuning embeddings from other standard pretraining approaches.

Shaoming Xu, Ankush Khandelwal, Arvind Renganathan et al.

Time series modeling, a crucial area in science, often encounters challenges when training Machine Learning (ML) models like Recurrent Neural Networks (RNNs) using the conventional mini-batch training strategy that assumes independent and identically distributed (IID) samples and initializes RNNs with zero hidden states. The IID assumption ignores temporal dependencies among samples, resulting in poor performance. This paper proposes the Message Propagation Through Time (MPTT) algorithm to effectively incorporate long temporal dependencies while preserving faster training times relative to the stateful solutions. MPTT utilizes two memory modules to asynchronously manage initial hidden states for RNNs, fostering seamless information exchange between samples and allowing diverse mini-batches throughout epochs. MPTT further implements three policies to filter outdated and preserve essential information in the hidden states to generate informative initial hidden states for RNNs, facilitating robust training. Experimental results demonstrate that MPTT outperforms seven strategies on four climate datasets with varying levels of temporal dependencies.

Arvind Renganathan, Rahul Ghosh, Ankush Khandelwal et al.

We introduce TAM-RL (Task Aware Modulation using Representation Learning), a novel multimodal meta-learning framework for few-shot learning in heterogeneous systems, designed for science and engineering problems where entities share a common underlying forward model but exhibit heterogeneity due to entity-specific characteristics. TAM-RL leverages an amortized training process with a modulation network and a base network to learn task-specific modulation parameters, enabling efficient adaptation to new tasks with limited data. We evaluate TAM-RL on two real-world environmental datasets: Gross Primary Product (GPP) prediction and streamflow forecasting, demonstrating significant improvements over existing meta-learning methods. On the FLUXNET dataset, TAM-RL improves RMSE by 18.9\% over MMAML with just one month of few-shot data, while for streamflow prediction, it achieves an 8.21\% improvement with one year of data. Synthetic data experiments further validate TAM-RL's superior performance in heterogeneous task distributions, outperforming the baselines in the most heterogeneous setting. Notably, TAM-RL offers substantial computational efficiency, with at least 3x faster training times compared to gradient-based meta-learning approaches while being much simpler to train due to reduced complexity. Ablation studies highlight the importance of pretraining and adaptation mechanisms in TAM-RL's performance.

Somya Sharma Chatterjee, Rahul Ghosh, Arvind Renganathan et al.

In hydrology, modeling streamflow remains a challenging task due to the limited availability of basin characteristics information such as soil geology and geomorphology. These characteristics may be noisy due to measurement errors or may be missing altogether. To overcome this challenge, we propose a knowledge-guided, probabilistic inverse modeling method for recovering physical characteristics from streamflow and weather data, which are more readily available. We compare our framework with state-of-the-art inverse models for estimating river basin characteristics. We also show that these estimates offer improvement in streamflow modeling as opposed to using the original basin characteristic values. Our inverse model offers 3\% improvement in R$^2$ for the inverse model (basin characteristic estimation) and 6\% for the forward model (streamflow prediction). Our framework also offers improved explainability since it can quantify uncertainty in both the inverse and the forward model. Uncertainty quantification plays a pivotal role in improving the explainability of machine learning models by providing additional insights into the reliability and limitations of model predictions. In our analysis, we assess the quality of the uncertainty estimates. Compared to baseline uncertainty quantification methods, our framework offers 10\% improvement in the dispersion of epistemic uncertainty and 13\% improvement in coverage rate. This information can help stakeholders understand the level of uncertainty associated with the predictions and provide a more comprehensive view of the potential outcomes.

Aleksei Rozanov, Arvind Renganathan, Yimeng Zhang et al.

Accurately quantifying terrestrial carbon exchange is essential for climate policy and carbon accounting, yet models must generalize to ecosystems underrepresented in sparse eddy covariance observations. Despite this challenge being a natural instance of zero-shot spatial transfer learning for time series regression, no standardized benchmark exists to rigorously evaluate model performance across geographically distinct locations with different climate regimes and vegetation types. We introduce CarbonBench, the first benchmark for zero-shot spatial transfer in carbon flux upscaling. CarbonBench comprises over 1.3 million daily observations from 567 flux tower sites globally (2000-2024). It provides: (1) stratified evaluation protocols that explicitly test generalization across unseen vegetation types and climate regimes, separating spatial transfer from temporal autocorrelation; (2) a harmonized set of remote sensing and meteorological features to enable flexible architecture design; and (3) baselines ranging from tree-based methods to domain-generalization architectures. By bridging machine learning methodologies and Earth system science, CarbonBench aims to enable systematic comparison of transfer learning methods, serves as a testbed for regression under distribution shift, and contributes to the next-generation climate modeling efforts.

Arka Daw, Anuj Karpatne, William Watkins et al.

This paper introduces a framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery. This framework, termed physics-guided neural networks (PGNN), leverages the output of physics-based model simulations along with observational features in a hybrid modeling setup to generate predictions using a neural network architecture. Further, this framework uses physics-based loss functions in the learning objective of neural networks to ensure that the model predictions not only show lower errors on the training set but are also scientifically consistent with the known physics on the unlabeled set. We illustrate the effectiveness of PGNN for the problem of lake temperature modeling, where physical relationships between the temperature, density, and depth of water are used to design a physics-based loss function. By using scientific knowledge to guide the construction and learning of neural networks, we are able to show that the proposed framework ensures better generalizability as well as scientific consistency of results. All the code and datasets used in this study have been made available on this link \url{https://github.com/arkadaw9/PGNN}.

Aleksei Rozanov, Arvind Renganathan, Vipin Kumar

Accurately upscaling terrestrial carbon fluxes is central to estimating the global carbon budget, yet remains challenging due to the sparse and regionally biased distribution of ground measurements. Existing data-driven upscaling products often fail to generalize beyond observed domains, leading to systematic regional biases and high predictive uncertainty. We introduce Task-Aware Modulation with Representation Learning (TAM-RL), a framework that couples spatio-temporal representation learning with knowledge-guided encoder-decoder architecture and loss function derived from the carbon balance equation. Across 150+ flux tower sites representing diverse biomes and climate regimes, TAM-RL improves predictive performance relative to existing state-of-the-art datasets, reducing RMSE by 8-9.6% and increasing explained variance (R2) from 19.4% to 43.8%, depending on the target flux. These results demonstrate that integrating physically grounded constraints with adaptive representation learning can substantially enhance the robustness and transferability of global carbon flux estimates.

Anuj Karpatne, Xiaowei Jia, Vipin Kumar

This paper presents an overview of scientific modeling and discusses the complementary strengths and weaknesses of ML methods for scientific modeling in comparison to process-based models. It also provides an introduction to the current state of research in the emerging field of scientific knowledge-guided machine learning (KGML) that aims to use both scientific knowledge and data in ML frameworks to achieve better generalizability, scientific consistency, and explainability of results. We discuss different facets of KGML research in terms of the type of scientific knowledge used, the form of knowledge-ML integration explored, and the method for incorporating scientific knowledge in ML. We also discuss some of the common categories of use cases in environmental sciences where KGML methods are being developed, using illustrative examples in each category.

Jia Li, Vipin Kumar, Rui Zhang

The dominant noun-based modeling paradigm has fundamentally constrained AI development, precluding any adequate representation of the future as an open temporal dimension. This paper introduces a verb-based paradigm, together with precise definitions of \emph{timing computation} and \emph{possibility}, that enables AI to function as an effective instrument for realizing the grammar of our thought. Applied to longitudinal EHR data from 3,276 breast cancer patients, the framework empirically demonstrates: (1) automatic discovery of clinically significant patient trajectories, and (2) counterfactual timing deduction. Both results are purely data-driven, require no prior domain knowledge, and, to our knowledge, represent the first such demonstrations in the machine learning literature.

Praveen Ravirathinam, Rahul Ghosh, Ankush Khandelwal et al.

Accurate and timely crop mapping is essential for yield estimation, insurance claims, and conservation efforts. Over the years, many successful machine learning models for crop mapping have been developed that use just the multi-spectral imagery from satellites to predict crop type over the area of interest. However, these traditional methods do not account for the physical processes that govern crop growth. At a high level, crop growth can be envisioned as physical parameters, such as weather and soil type, acting upon the plant leading to crop growth which can be observed via satellites. In this paper, we propose Weather-based Spatio-Temporal segmentation network with ATTention (WSTATT), a deep learning model that leverages this understanding of crop growth by formulating it as an inverse model that combines weather (Daymet) and satellite imagery (Sentinel-2) to generate accurate crop maps. We show that our approach provides significant improvements over existing algorithms that solely rely on spectral imagery by comparing segmentation maps and F1 classification scores. Furthermore, effective use of attention in WSTATT architecture enables detection of crop types earlier in the season (up to 5 months in advance), which is very useful for improving food supply projections. We finally discuss the impact of weather by correlating our results with crop phenology to show that WSTATT is able to capture physical properties of crop growth.

Jared D. Willard, Fabio Ciulla, Helen Weierbach et al.

The prediction of streamflows and other environmental variables in unmonitored basins is a grand challenge in hydrology. Recent machine learning (ML) models can harness vast datasets for accurate predictions at large spatial scales. However, there are open questions regarding model design and data needed for inputs and training to improve performance. This study explores these questions while demonstrating the ability of deep learning models to make accurate stream temperature predictions in unmonitored basins across the conterminous United States. First, we compare top-down models that utilize data from a large number of basins with bottom-up methods that transfer ML models built on local sites, reflecting traditional regionalization techniques. We also evaluate an intermediary grouped modeling approach that categorizes sites based on regional co-location or similarity of catchment characteristics. Second, we evaluate trade-offs between model complexity, prediction accuracy, and applicability for more target locations by systematically removing inputs. We then examine model performance when additional training data becomes available due to reductions in input requirements. Our results suggest that top-down models significantly outperform bottom-up and grouped models. Moreover, it is possible to get acceptable accuracy by reducing both dynamic and static inputs enabling predictions for more sites with lower model complexity and computational needs. From detailed error analysis, we determined that the models are more accurate for sites primarily controlled by air temperatures compared to locations impacted by groundwater and dams. By addressing these questions, this research offers a comprehensive perspective on optimizing ML model design for accurate predictions in unmonitored regions.

Shaoming Xu, Arvind Renganathan, Ankush Khandelwal et al.

Streamflow, vital for water resource management, is governed by complex hydrological systems involving intermediate processes driven by meteorological forces. While deep learning models have achieved state-of-the-art results of streamflow prediction, their end-to-end single-task learning approach often fails to capture the causal relationships within these systems. To address this, we propose Hierarchical Conditional Multi-Task Learning (HCMTL), a hierarchical approach that jointly models soil water and snowpack processes based on their causal connections to streamflow. HCMTL utilizes task embeddings to connect network modules, enhancing flexibility and expressiveness while capturing unobserved processes beyond soil water and snowpack. It also incorporates the Conditional Mini-Batch strategy to improve long time series modeling. We compare HCMTL with five baselines on a global dataset. HCMTL's superior performance across hundreds of drainage basins over extended periods shows that integrating domain-specific causal knowledge into deep learning enhances both prediction accuracy and interpretability. This is essential for advancing our understanding of complex hydrological systems and supporting efficient water resource management to mitigate natural disasters like droughts and floods.

Kshitij Tayal, Arvind Renganathan, Xiaowei Jia et al.

Accurate long-term predictions are the foundations for many machine learning applications and decision-making processes. Traditional time series approaches for prediction often focus on either autoregressive modeling, which relies solely on past observations of the target ``endogenous variables'', or forward modeling, which considers only current covariate drivers ``exogenous variables''. However, effectively integrating past endogenous and past exogenous with current exogenous variables remains a significant challenge. In this paper, we propose ExoTST, a novel transformer-based framework that effectively incorporates current exogenous variables alongside past context for improved time series prediction. To integrate exogenous information efficiently, ExoTST leverages the strengths of attention mechanisms and introduces a novel cross-temporal modality fusion module. This module enables the model to jointly learn from both past and current exogenous series, treating them as distinct modalities. By considering these series separately, ExoTST provides robustness and flexibility in handling data uncertainties that arise from the inherent distribution shift between historical and current exogenous variables. Extensive experiments on real-world carbon flux datasets and time series benchmarks demonstrate ExoTST's superior performance compared to state-of-the-art baselines, with improvements of up to 10\% in prediction accuracy. Moreover, ExoTST exhibits strong robustness against missing values and noise in exogenous drivers, maintaining consistent performance in real-world situations where these imperfections are common.

Yilong Dai, Shengyu Chen, Ziyi Wang et al.

Partial differential equations (PDEs) are central to scientific modeling. Modern workflows increasingly rely on learning-based components to support model reuse, inference, and integration across large computational processes. Despite the emergence of various physics-aware data-driven approaches, the field still lacks a unified perspective to uncover their relationships, limitations, and appropriate roles in scientific workflows. To this end, we propose a unifying perspective to place two dominant paradigms: Physics-Informed Neural Networks (PINNs) and Neural Operators (NOs), within a shared design space. We organize existing methods from three fundamental dimensions: what is learned, how physical structures are integrated into the learning process, and how the computational load is amortized across problem instances. In this way, many challenges can be best understood as consequences of these structural properties of learning PDEs. By analyzing advances through this unifying view, our survey aims to facilitate the development of reliable learning-based PDE solvers and catalyze a synthesis of physics and data.

Rahul Ghosh, Arvind Renganathan, Kshitij Tayal et al.

Machine Learning is beginning to provide state-of-the-art performance in a range of environmental applications such as streamflow prediction in a hydrologic basin. However, building accurate broad-scale models for streamflow remains challenging in practice due to the variability in the dominant hydrologic processes, which are best captured by sets of process-related basin characteristics. Existing basin characteristics suffer from noise and uncertainty, among many other things, which adversely impact model performance. To tackle the above challenges, in this paper, we propose a novel Knowledge-guided Self-Supervised Learning (KGSSL) inverse framework to extract system characteristics from driver and response data. This first-of-its-kind framework achieves robust performance even when characteristics are corrupted. We show that KGSSL achieves state-of-the-art results for streamflow modeling for CAMELS (Catchment Attributes and MEteorology for Large-sample Studies) which is a widely used hydrology benchmark dataset. Specifically, KGSSL outperforms other methods by up to 16 \% in reconstructing characteristics. Furthermore, we show that KGSSL is relatively more robust to distortion than baseline methods, and outperforms the baseline model by 35\% when plugging in KGSSL inferred characteristics.

Guruprasad Nayak, Rahul Ghosh, Xiaowei Jia et al.

In many applications, finding adequate labeled data to train predictive models is a major challenge. In this work, we propose methods to use group-level binary labels as weak supervision to train instance-level binary classification models. Aggregate labels are common in several domains where annotating on a group-level might be cheaper or might be the only way to provide annotated data without infringing on privacy. We model group-level labels as Class Conditional Noisy (CCN) labels for individual instances and use the noisy labels to regularize predictions of the model trained on the strongly-labeled instances. Our experiments on real-world application of land cover mapping shows the utility of the proposed method in leveraging group-level labels, both in the presence and absence of class imbalance.

Rahul Ghosh, Xiaowei Jia, Chenxi Lin et al.

Collecting large annotated datasets in Remote Sensing is often expensive and thus can become a major obstacle for training advanced machine learning models. Common techniques of addressing this issue, based on the underlying idea of pre-training the Deep Neural Networks (DNN) on freely available large datasets, cannot be used for Remote Sensing due to the unavailability of such large-scale labeled datasets and the heterogeneity of data sources caused by the varying spatial and spectral resolution of different sensors. Self-supervised learning is an alternative approach that learns feature representation from unlabeled images without using any human annotations. In this paper, we introduce a new method for land cover mapping by using a clustering based pretext task for self-supervised learning. We demonstrate the effectiveness of the method on two societally relevant applications from the aspect of segmentation performance, discriminative feature representation learning and the underlying cluster structure. We also show the effectiveness of the active sampling using the clusters obtained from our method in improving the mapping accuracy given a limited budget of annotating.

Rahul Ghosh, Praveen Ravirathinam, Xiaowei Jia et al.

Mapping and monitoring crops is a key step towards sustainable intensification of agriculture and addressing global food security. A dataset like ImageNet that revolutionized computer vision applications can accelerate development of novel crop mapping techniques. Currently, the United States Department of Agriculture (USDA) annually releases the Cropland Data Layer (CDL) which contains crop labels at 30m resolution for the entire United States of America. While CDL is state of the art and is widely used for a number of agricultural applications, it has a number of limitations (e.g., pixelated errors, labels carried over from previous errors and absence of input imagery along with class labels). In this work, we create a new semantic segmentation benchmark dataset, which we call CalCROP21, for the diverse crops in the Central Valley region of California at 10m spatial resolution using a Google Earth Engine based robust image processing pipeline and a novel attention based spatio-temporal semantic segmentation algorithm STATT. STATT uses re-sampled (interpolated) CDL labels for training, but is able to generate a better prediction than CDL by leveraging spatial and temporal patterns in Sentinel2 multi-spectral image series to effectively capture phenologic differences amongst crops and uses attention to reduce the impact of clouds and other atmospheric disturbances. We also present a comprehensive evaluation to show that STATT has significantly better results when compared to the resampled CDL labels. We have released the dataset and the processing pipeline code for generating the benchmark dataset.

Kshitij Tayal, Raunak Manekar, Zhong Zhuang et al.

Several deep learning methods for phase retrieval exist, but most of them fail on realistic data without precise support information. We propose a novel method based on single-instance deep generative prior that works well on complex-valued crystal data.

Rahul Ghosh, Praveen Ravirathinam, Xiaowei Jia et al.

The availability of massive earth observing satellite data provide huge opportunities for land use and land cover mapping. However, such mapping effort is challenging due to the existence of various land cover classes, noisy data, and the lack of proper labels. Also, each land cover class typically has its own unique temporal pattern and can be identified only during certain periods. In this article, we introduce a novel architecture that incorporates the UNet structure with Bidirectional LSTM and Attention mechanism to jointly exploit the spatial and temporal nature of satellite data and to better identify the unique temporal patterns of each land cover. We evaluate this method for mapping crops in multiple regions over the world. We compare our method with other state-of-the-art methods both quantitatively and qualitatively on two real-world datasets which involve multiple land cover classes. We also visualise the attention weights to study its effectiveness in mitigating noise and identifying discriminative time period.

Rahul Ghosh, Xiaowei Jia, Vipin Kumar

Land cover mapping is essential for monitoring global environmental change and managing natural resources. Unfortunately, traditional classification models are plagued by limited training data available in existing land cover products and data heterogeneity over space and time. In this survey, we provide a structured and comprehensive overview of challenges in land cover mapping and machine learning methods used to address these problems. We also discuss the gaps and opportunities that exist for advancing research in this promising direction.

Ankush Khandelwal, Shaoming Xu, Xiang Li et al.

Streamflow prediction is one of the key challenges in the field of hydrology due to the complex interplay between multiple non-linear physical mechanisms behind streamflow generation. While physics based models are rooted in rich understanding of the physical processes, a significant performance gap still remains which can be potentially addressed by leveraging the recent advances in machine learning. The goal of this work is to incorporate our understanding of hydrological processes and constraints into machine learning algorithms to improve the predictive performance. Traditional ML models for this problem predict streamflow using weather drivers as input. However there are multiple intermediate processes that interact to generate streamflow from weather drivers. The key idea of the approach is to explicitly model these intermediate processes that connect weather drivers to streamflow using a multi-task learning framework. While our proposed approach requires data about intermediate processes during training, only weather drivers will be needed to predict the streamflow during testing phase. We assess the efficacy of the approach on a simulation dataset generated by the SWAT model for a catchment located in the South Branch of the Root River Watershed in southeast Minnesota. While the focus of this paper is on improving the performance given data from a single catchment, methodology presented here is applicable to ML-based approaches that use data from multiple catchments to improve performance of each individual catchment.

Jia Li, Haoyu Yang, Xiaowei Jia et al.

Electronic Health Records (EHR) data analysis plays a crucial role in healthcare system quality. Because of its highly complex underlying causality and limited observable nature, causal inference on EHR is quite challenging. Deep Learning (DL) achieved great success among the advanced machine learning methodologies. Nevertheless, it is still obstructed by the inappropriately assumed causal conditions. This work proposed a novel method to quantify clinically well-defined causal effects as a generalized estimation vector that is simply utilizable for causal models. We incorporated it into DL models to achieve better predictive performance and result interpretation. Furthermore, we also proved the existence of causal information blink spots that regular DL models cannot reach.

Jared D. Willard, Jordan S. Read, Alison P. Appling et al.

Most environmental data come from a minority of well-monitored sites. An ongoing challenge in the environmental sciences is transferring knowledge from monitored sites to unmonitored sites. Here, we demonstrate a novel transfer learning framework that accurately predicts depth-specific temperature in unmonitored lakes (targets) by borrowing models from well-monitored lakes (sources). This method, Meta Transfer Learning (MTL), builds a meta-learning model to predict transfer performance from candidate source models to targets using lake attributes and candidates' past performance. We constructed source models at 145 well-monitored lakes using calibrated process-based modeling (PB) and a recently developed approach called process-guided deep learning (PGDL). We applied MTL to either PB or PGDL source models (PB-MTL or PGDL-MTL, respectively) to predict temperatures in 305 target lakes treated as unmonitored in the Upper Midwestern United States. We show significantly improved performance relative to the uncalibrated process-based General Lake Model, where the median RMSE for the target lakes is $2.52^{\circ}C$. PB-MTL yielded a median RMSE of $2.43^{\circ}C$; PGDL-MTL yielded $2.16^{\circ}C$; and a PGDL-MTL ensemble of nine sources per target yielded $1.88^{\circ}C$. For sparsely monitored target lakes, PGDL-MTL often outperformed PGDL models trained on the target lakes themselves. Differences in maximum depth between the source and target were consistently the most important predictors. Our approach readily scales to thousands of lakes in the Midwestern United States, demonstrating that MTL with meaningful predictor variables and high-quality source models is a promising approach for many kinds of unmonitored systems and environmental variables.

Xiaowei Jia, Jacob Zwart, Jeffrey Sadler et al.

This paper proposes a physics-guided machine learning approach that combines advanced machine learning models and physics-based models to improve the prediction of water flow and temperature in river networks. We first build a recurrent graph network model to capture the interactions among multiple segments in the river network. Then we present a pre-training technique which transfers knowledge from physics-based models to initialize the machine learning model and learn the physics of streamflow and thermodynamics. We also propose a new loss function that balances the performance over different river segments. We demonstrate the effectiveness of the proposed method in predicting temperature and streamflow in a subset of the Delaware River Basin. In particular, we show that the proposed method brings a 33\%/14\% improvement over the state-of-the-art physics-based model and 24\%/14\% over traditional machine learning models (e.g., Long-Short Term Memory Neural Network) in temperature/streamflow prediction using very sparse (0.1\%) observation data for training. The proposed method has also been shown to produce better performance when generalized to different seasons or river segments with different streamflow ranges.

Kshitij Tayal, Chieh-Hsin Lai, Vipin Kumar et al.

In many physical systems, inputs related by intrinsic system symmetries are mapped to the same output. When inverting such systems, i.e., solving the associated inverse problems, there is no unique solution. This causes fundamental difficulties for deploying the emerging end-to-end deep learning approach. Using the generalized phase retrieval problem as an illustrative example, we show that careful symmetry breaking on the training data can help get rid of the difficulties and significantly improve the learning performance. We also extract and highlight the underlying mathematical principle of the proposed solution, which is directly applicable to other inverse problems.

Jared Willard, Xiaowei Jia, Shaoming Xu et al.

There is a growing consensus that solutions to complex science and engineering problems require novel methodologies that are able to integrate traditional physics-based modeling approaches with state-of-the-art machine learning (ML) techniques. This paper provides a structured overview of such techniques. Application-centric objective areas for which these approaches have been applied are summarized, and then classes of methodologies used to construct physics-guided ML models and hybrid physics-ML frameworks are described. We then provide a taxonomy of these existing techniques, which uncovers knowledge gaps and potential crossovers of methods between disciplines that can serve as ideas for future research.

Xiaowei Jia, Jared Willard, Anuj Karpatne et al.

Physics-based models of dynamical systems are often used to study engineering and environmental systems. Despite their extensive use, these models have several well-known limitations due to simplified representations of the physical processes being modeled or challenges in selecting appropriate parameters. While-state-of-the-art machine learning models can sometimes outperform physics-based models given ample amount of training data, they can produce results that are physically inconsistent. This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improves the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physics-based models, while generating outputs consistent with physical laws. An important aspect of our PGRNN approach lies in its ability to incorporate the knowledge encoded in physics-based models. This allows training the PGRNN model using very few true observed data while also ensuring high prediction accuracy. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where physics-based (also known as mechanistic) models are used, e.g., climate science, materials science, computational chemistry, and biomedicine.

Guruprasad Nayak, Rahul Ghosh, Xiaowei Jia et al.

Many real-world phenomena are observed at multiple resolutions. Predictive models designed to predict these phenomena typically consider different resolutions separately. This approach might be limiting in applications where predictions are desired at fine resolutions but available training data is scarce. In this paper, we propose classification algorithms that leverage supervision from coarser resolutions to help train models on finer resolutions. The different resolutions are modeled as different views of the data in a multi-view framework that exploits the complementarity of features across different views to improve models on both views. Unlike traditional multi-view learning problems, the key challenge in our case is that there is no one-to-one correspondence between instances across different views in our case, which requires explicit modeling of the correspondence of instances across resolutions. We propose to use the features of instances at different resolutions to learn the correspondence between instances across resolutions using an attention mechanism.Experiments on the real-world application of mapping urban areas using satellite observations and sentiment classification on text data show the effectiveness of the proposed methods.

Saurabh Agrawal, Saurabh Verma, Anuj Karpatne et al.

Traditional approaches focus on finding relationships between two entire time series, however, many interesting relationships exist in small sub-intervals of time and remain feeble during other sub-intervals. We define the notion of a sub-interval relationship (SIR) to capture such interactions that are prominent only in certain sub-intervals of time. To that end, we propose a fast-optimal guaranteed algorithm to find most interesting SIR relationship in a pair of time series. Lastly, we demonstrate the utility of our method in climate science domain based on a real-world dataset along with its scalability scope and obtain useful domain insights.

Xiaowei Jia, Ankush Khandelwal, Vipin Kumar

This paper provides an overview of how recent advances in machine learning and the availability of data from earth observing satellites can dramatically improve our ability to automatically map croplands over long period and over large regions. It discusses three applications in the domain of crop monitoring where ML approaches are beginning to show great promise. For each application, it highlights machine learning challenges, proposed approaches, and recent results. The paper concludes with discussion of major challenges that need to be addressed before ML approaches will reach their full potential for this problem of great societal relevance.

Xiaowei Jia, Jared Willard, Anuj Karpatne et al.

This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physical models, while generating outputs consistent with physical laws, and achieving good generalizability. Standard RNNs, even when producing superior prediction accuracy, often produce physically inconsistent results and lack generalizability. We further enhance this approach by using a pre-training method that leverages the simulated data from a physics-based model to address the scarcity of observed data. The PGRNN has the flexibility to incorporate additional physical constraints and we incorporate a density-depth relationship. Both enhancements further improve PGRNN performance. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where mechanistic (also known as process-based) models are used, e.g., power engineering, climate science, materials science, computational chemistry, and biomedicine.

Saurabh Agrawal, Michael Steinbach, Daniel Boley et al.

In many domains, there is significant interest in capturing novel relationships between time series that represent activities recorded at different nodes of a highly complex system. In this paper, we introduce multipoles, a novel class of linear relationships between more than two time series. A multipole is a set of time series that have strong linear dependence among themselves, with the requirement that each time series makes a significant contribution to the linear dependence. We demonstrate that most interesting multipoles can be identified as cliques of negative correlations in a correlation network. Such cliques are typically rare in a real-world correlation network, which allows us to find almost all multipoles efficiently using a clique-enumeration approach. Using our proposed framework, we demonstrate the utility of multipoles in discovering new physical phenomena in two scientific domains: climate science and neuroscience. In particular, we discovered several multipole relationships that are reproducible in multiple other independent datasets and lead to novel domain insights.

Xiaowei Jia, Anuj Karpatne, Jared Willard et al.

In this paper, we introduce a novel framework for combining scientific knowledge within physics-based models and recurrent neural networks to advance scientific discovery in many dynamical systems. We will first describe the use of outputs from physics-based models in learning a hybrid-physics-data model. Then, we further incorporate physical knowledge in real-world dynamical systems as additional constraints for training recurrent neural networks. We will apply this approach on modeling lake temperature and quality where we take into account the physical constraints along both the depth dimension and time dimension. By using scientific knowledge to guide the construction and learning the data-driven model, we demonstrate that this method can achieve better prediction accuracy as well as scientific consistency of results.

Saurabh Agrawal, Saurabh Verma, Gowtham Atluri et al.

Time-series data is being increasingly collected and stud- ied in several areas such as neuroscience, climate science, transportation, and social media. Discovery of complex patterns of relationships between individual time-series, using data-driven approaches can improve our understanding of real-world systems. While traditional approaches typically study relationships between two entire time series, many interesting relationships in real-world applications exist in small sub-intervals of time while remaining absent or feeble during other sub-intervals. In this paper, we define the notion of a sub-interval relationship (SIR) to capture inter- actions between two time series that are prominent only in certain sub-intervals of time. We propose a novel and efficient approach to find most interesting SIR in a pair of time series. We evaluate our proposed approach on two real-world datasets from climate science and neuroscience domain and demonstrated the scalability and computational efficiency of our proposed approach. We further evaluated our discovered SIRs based on a randomization based procedure. Our results indicated the existence of several such relationships that are statistically significant, some of which were also found to have physical interpretation.