Hendrik F. Hamann

Johannes Schmude, Sujit Roy, Will Trojak et al.

Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecasting, downscaling, or nowcasting. While the parallel developments in the AI literature focus on foundation models -- models that can be effectively tuned to address multiple, different use cases -- the developments on the weather and climate side largely focus on single-use cases with particular emphasis on mid-range forecasting. We close this gap by introducing Prithvi WxC, a 2.3 billion parameter foundation model developed using 160 variables from the Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). Prithvi WxC employs an encoder-decoder-based architecture, incorporating concepts from various recent transformer models to effectively capture both regional and global dependencies in the input data. The model has been designed to accommodate large token counts to model weather phenomena in different topologies at fine resolutions. Furthermore, it is trained with a mixed objective that combines the paradigms of masked reconstruction with forecasting. We test the model on a set of challenging downstream tasks namely: Autoregressive rollout forecasting, Downscaling, Gravity wave flux parameterization, and Extreme events estimation. The pretrained model with 2.3 billion parameters, along with the associated fine-tuning workflows, has been publicly released as an open-source contribution via Hugging Face.

Hendrik F. Hamann, Thomas Brunschwiler, Blazhe Gjorgiev et al.

Foundation models (FMs) currently dominate news headlines. They employ advanced deep learning architectures to extract structural information autonomously from vast datasets through self-supervision. The resulting rich representations of complex systems and dynamics can be applied to many downstream applications. Therefore, FMs can find uses in electric power grids, challenged by the energy transition and climate change. In this paper, we call for the development of, and state why we believe in, the potential of FMs for electric grids. We highlight their strengths and weaknesses amidst the challenges of a changing grid. We argue that an FM learning from diverse grid data and topologies could unlock transformative capabilities, pioneering a new approach in leveraging AI to redefine how we manage complexity and uncertainty in the electric grid. Finally, we discuss a power grid FM concept, namely GridFM, based on graph neural networks and show how different downstream tasks benefit.

Xuying Ning, Dongqi Fu, Tianxin Wei et al.

With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve-then-generate paradigm toward more sophisticated agentic multimodal retrieval-augmented generation (MM-RAG). Existing benchmarks, however, mainly focus on simplified QA with short retrieval chains, leaving adaptive planning and multimodal reasoning underexplored. We present MC-Search, the first benchmark for agentic MM-RAG with long, step-wise annotated reasoning chains spanning five representative reasoning structures. Each example specifies sub-questions, retrieval modalities, supporting facts, and intermediate answers, with fidelity ensured by HAVE (Hop-wise Attribution and Verification of Evidence), resulting in 3,333 high-quality examples averaging 3.7 hops. Beyond answer accuracy, MC-Search introduces new process-level metrics for reasoning quality, stepwise retrieval and planning accuracy. By developing a unified agentic MM-RAG pipeline, we benchmark six leading MLLMs and reveal systematic issues such as over- and under-retrieval and modality-misaligned planning. Finally, we introduce Search-Align, a process-supervised fine-tuning framework leveraging verified reasoning chains, showing that our data not only enables faithful evaluation but also improves planning and retrieval fidelity in open-source MLLMs.

S. Karthik Mukkavilli, Daniel Salles Civitarese, Johannes Schmude et al.

Machine learning and deep learning methods have been widely explored in understanding the chaotic behavior of the atmosphere and furthering weather forecasting. There has been increasing interest from technology companies, government institutions, and meteorological agencies in building digital twins of the Earth. Recent approaches using transformers, physics-informed machine learning, and graph neural networks have demonstrated state-of-the-art performance on relatively narrow spatiotemporal scales and specific tasks. With the recent success of generative artificial intelligence (AI) using pre-trained transformers for language modeling and vision with prompt engineering and fine-tuning, we are now moving towards generalizable AI. In particular, we are witnessing the rise of AI foundation models that can perform competitively on multiple domain-specific downstream tasks. Despite this progress, we are still in the nascent stages of a generalizable AI model for global Earth system models, regional climate models, and mesoscale weather models. Here, we review current state-of-the-art AI approaches, primarily from transformer and operator learning literature in the context of meteorology. We provide our perspective on criteria for success towards a family of foundation models for nowcasting and forecasting weather and climate predictions. We also discuss how such models can perform competitively on downstream tasks such as downscaling (super-resolution), identifying conditions conducive to the occurrence of wildfires, and predicting consequential meteorological phenomena across various spatiotemporal scales such as hurricanes and atmospheric rivers. In particular, we examine current AI methodologies and contend they have matured enough to design and implement a weather foundation model.

Romeo Kienzler, Leonardo Pondian Tizzei, Benedikt Blumenstiel et al.

Storing and streaming high dimensional data for foundation model training became a critical requirement with the rise of foundation models beyond natural language. In this paper we introduce TensorBank, a petabyte scale tensor lakehouse capable of streaming tensors from Cloud Object Store (COS) to GPU memory at wire speed based on complex relational queries. We use Hierarchical Statistical Indices (HSI) for query acceleration. Our architecture allows to directly address tensors on block level using HTTP range reads. Once in GPU memory, data can be transformed using PyTorch transforms. We provide a generic PyTorch dataset type with a corresponding dataset factory translating relational queries and requested transformations as an instance. By making use of the HSI, irrelevant blocks can be skipped without reading them as those indices contain statistics on their content at different hierarchical resolution levels. This is an opinionated architecture powered by open standards and making heavy use of open-source technology. Although, hardened for production use using geospatial-temporal data, this architecture generalizes to other use case like computer vision, computational neuroscience, biological sequence analysis and more.

Alban Puech, Matteo Mazzonelli, Celia Cintas et al.

We introduce gridfm-datakit-v1, a Python library for generating realistic and diverse Power Flow (PF) and Optimal Power Flow (OPF) datasets for training Machine Learning (ML) solvers. Existing datasets and libraries face three main challenges: (1) lack of realistic stochastic load and topology perturbations, limiting scenario diversity; (2) PF datasets are restricted to OPF-feasible points, hindering generalization of ML solvers to cases that violate operating limits (e.g., branch overloads or voltage violations); and (3) OPF datasets use fixed generator cost functions, limiting generalization across varying costs. gridfm-datakit addresses these challenges by: (1) combining global load scaling from real-world profiles with localized noise and supporting arbitrary N-k topology perturbations to create diverse yet realistic datasets; (2) generating PF samples beyond operating limits; and (3) producing OPF data with varying generator costs. It also scales efficiently to large grids (up to 10,000 buses). Comparisons with OPFData, OPF-Learn, PGLearn, and PF$Δ$ are provided. Available on GitHub at https://github.com/gridfm/gridfm-datakit under Apache 2.0 and via `pip install gridfm-datakit`.

Zihao Li, Xiao Lin, Zhining Liu et al.

While many advances in time series models focus exclusively on numerical data, research on multimodal time series, particularly those involving contextual textual information commonly encountered in real-world scenarios, remains in its infancy. With recent progress in large language models and time series learning, we revisit the integration of paired texts with time series through the Platonic Representation Hypothesis, which posits that representations of different modalities converge to shared spaces. In this context, we identify that time-series-paired texts may naturally exhibit periodic properties that closely mirror those of the original time series. Building on this insight, we propose a novel framework, Texts as Time Series (TaTS), which considers the time-series-paired texts to be auxiliary variables of the time series. TaTS can be plugged into any existing numerical-only time series models and enable them to handle time series data with paired texts effectively. Through extensive experiments on both multimodal time series forecasting and imputation tasks across benchmark datasets with various existing time series models, we demonstrate that TaTS can enhance predictive performance without modifying model architectures. Code available at https://github.com/iDEA-iSAIL-Lab-UIUC/TaTS.

Yuanchen Bei, Tianxin Wei, Xuying Ning et al.

Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over time. However, existing benchmarks either evaluate multi-session memory in text-only conversations or assess multimodal understanding within localized contexts, failing to evaluate how multimodal memory is preserved, organized, and evolved across long-term conversational trajectories. Thus, we introduce Mem-Gallery, a new benchmark for evaluating multimodal long-term conversational memory in MLLM agents. Mem-Gallery features high-quality multi-session conversations grounded in both visual and textual information, with long interaction horizons and rich multimodal dependencies. Building on this dataset, we propose a systematic evaluation framework that assesses key memory capabilities along three functional dimensions: memory extraction and test-time adaptation, memory reasoning, and memory knowledge management. Extensive benchmarking across thirteen memory systems reveals several key findings, highlighting the necessity of explicit multimodal information retention and memory organization, the persistent limitations in memory reasoning and knowledge management, as well as the efficiency bottleneck of current models.

Zhining Liu, Ze Yang, Xiao Lin et al.

Time-series forecasting plays a critical role in many real-world applications. Although increasingly powerful models have been developed and achieved superior results on benchmark datasets, through a fine-grained sample-level inspection, we find that (i) no single model consistently outperforms others across different test samples, but instead (ii) each model excels in specific cases. These findings prompt us to explore how to adaptively leverage the distinct strengths of various forecasting models for different samples. We introduce TimeFuse, a framework for collective time-series forecasting with sample-level adaptive fusion of heterogeneous models. TimeFuse utilizes meta-features to characterize input time series and trains a learnable fusor to predict optimal model fusion weights for any given input. The fusor can leverage samples from diverse datasets for joint training, allowing it to adapt to a wide variety of temporal patterns and thus generalize to new inputs, even from unseen datasets. Extensive experiments demonstrate the effectiveness of TimeFuse in various long-/short-term forecasting tasks, achieving near-universal improvement over the state-of-the-art individual models. Code is available at https://github.com/ZhiningLiu1998/TimeFuse.

Alban Puech, Jonas Weiss, Thomas Brunschwiler et al.

The energy transition, crucial for tackling the climate crisis, demands integrating numerous distributed, renewable energy sources into existing grids. Along with climate change and consumer behavioral changes, this leads to changes and variability in generation and load patterns, introducing significant complexity and uncertainty into grid planning and operations. While the industry has already started to exploit AI to overcome computational challenges of established grid simulation tools, we propose the use of AI Foundation Models (FMs) and advances in Graph Neural Networks to efficiently exploit poorly available grid data for different downstream tasks, enhancing grid operations. For capturing the grid's underlying physics, we believe that building a self-supervised model learning the power flow dynamics is a critical first step towards developing an FM for the power grid. We show how this approach may close the gap between the industry needs and current grid analysis capabilities, to bring the industry closer to optimal grid operation and planning.

Alban Puech, François Mirallès, Jonas Weiss et al.

Quasi-static time series (QSTS) simulations have great potential for evaluating the grid's ability to accommodate the large-scale integration of distributed energy resources. However, as grids expand and operate closer to their limits, iterative power flow solvers, central to QSTS simulations, become computationally prohibitive and face increasing convergence issues. Neural power flow solvers provide a promising alternative, speeding up power flow computations by 3 to 4 orders of magnitude, though they are costly to train. In this paper, we envision how recently introduced grid foundation models could improve the economic viability of neural power flow solvers. Conceptually, these models amortize training costs by serving as a foundation for a range of grid operation and planning tasks beyond power flow solving, with only minimal fine-tuning required. We call for collaboration between the AI and power grid communities to develop and open-source these models, enabling all operators, even those with limited resources, to benefit from AI without building solutions from scratch.

Zhining Liu, Ruizhong Qiu, Zhichen Zeng et al.

Data collected in the real world often encapsulates historical discrimination against disadvantaged groups and individuals. Existing fair machine learning (FairML) research has predominantly focused on mitigating discriminative bias in the model prediction, with far less effort dedicated towards exploring how to trace biases present in the data, despite its importance for the transparency and interpretability of FairML. To fill this gap, we investigate a novel research problem: discovering samples that reflect biases/prejudices from the training data. Grounding on the existing fairness notions, we lay out a sample bias criterion and propose practical algorithms for measuring and countering sample bias. The derived bias score provides intuitive sample-level attribution and explanation of historical bias in data. On this basis, we further design two FairML strategies via sample-bias-informed minimal data editing. They can mitigate both group and individual unfairness at the cost of minimal or zero predictive utility loss. Extensive experiments and analyses on multiple real-world datasets demonstrate the effectiveness of our methods in explaining and mitigating unfairness. Code is available at https://github.com/ZhiningLiu1998/AIM.

Deming Chen, Alaa Youssef, Ruchi Pendse et al.

This white paper, developed through close collaboration between IBM Research and UIUC researchers within the IIDAI Institute, envisions transforming hybrid cloud systems to meet the growing complexity of AI workloads through innovative, full-stack co-design approaches, emphasizing usability, manageability, affordability, adaptability, efficiency, and scalability. By integrating cutting-edge technologies such as generative and agentic AI, cross-layer automation and optimization, unified control plane, and composable and adaptive system architecture, the proposed framework addresses critical challenges in energy efficiency, performance, and cost-effectiveness. Incorporating quantum computing as it matures will enable quantum-accelerated simulations for materials science, climate modeling, and other high-impact domains. Collaborative efforts between academia and industry are central to this vision, driving advancements in foundation models for material design and climate solutions, scalable multimodal data processing, and enhanced physics-based AI emulators for applications like weather forecasting and carbon sequestration. Research priorities include advancing AI agentic systems, LLM as an Abstraction (LLMaaA), AI model optimization and unified abstractions across heterogeneous infrastructure, end-to-end edge-cloud transformation, efficient programming model, middleware and platform, secure infrastructure, application-adaptive cloud systems, and new quantum-classical collaborative workflows. These ideas and solutions encompass both theoretical and practical research questions, requiring coordinated input and support from the research community. This joint initiative aims to establish hybrid clouds as secure, efficient, and sustainable platforms, fostering breakthroughs in AI-driven applications and scientific discovery across academia, industry, and society.

Masato Sakai, Marcus Freitag, Akihisa Sakurai et al.

Preservation of the Nasca geoglyphs at the UNESCO World Heritage Site in Peru is urgent as natural and human impact accelerates. More frequent weather extremes such as flashfloods threaten Nasca artifacts. We demonstrate that runoff models based on (sub-)meter scale, LiDAR-derived digital elevation data can highlight AI-detected geoglyphs that are in danger of erosion. We recommend measures of mitigation to protect the famous "lizard", "tree", and "hand" geoglyphs located close by, or even cut by the Pan-American Highway.

Wang Zhou, Shiyu Chang, Norma Sosa et al.

Recent advances in object detection have benefited significantly from rapid developments in deep neural networks. However, neural networks suffer from the well-known issue of catastrophic forgetting, which makes continual or lifelong learning problematic. In this paper, we leverage the fact that new training classes arrive in a sequential manner and incrementally refine the model so that it additionally detects new object classes in the absence of previous training data. Specifically, we consider the representative object detector, Faster R-CNN, for both accurate and efficient prediction. To prevent abrupt performance degradation due to catastrophic forgetting, we propose to apply knowledge distillation on both the region proposal network and the region classification network, to retain the detection of previously trained classes. A pseudo-positive-aware sampling strategy is also introduced for distillation sample selection. We evaluate the proposed method on PASCAL VOC 2007 and MS COCO benchmarks and show competitive mAP and 6x inference speed improvement, which makes the approach more suitable for real-time applications. Our implementation will be publicly available.

Conrad M Albrecht, Chris Fisher, Marcus Freitag et al.

We present a remote sensing pipeline that processes LiDAR (Light Detection And Ranging) data through machine & deep learning for the application of archeological feature detection on big geo-spatial data platforms such as e.g. IBM PAIRS Geoscope. Today, archeologists get overwhelmed by the task of visually surveying huge amounts of (raw) LiDAR data in order to identify areas of interest for inspection on the ground. We showcase a software system pipeline that results in significant savings in terms of expert productivity while missing only a small fraction of the artifacts. Our work employs artificial neural networks in conjunction with an efficient spatial segmentation procedure based on domain knowledge. Data processing is constraint by a limited amount of training labels and noisy LiDAR signals due to vegetation cover and decay of ancient structures. We aim at identifying geo-spatial areas with archeological artifacts in a supervised fashion allowing the domain expert to flexibly tune parameters based on her needs.

Cong Feng, Mingjian Cui, Bri-Mathias Hodge et al.

Solar forecasting accuracy is affected by weather conditions, and weather awareness forecasting models are expected to improve the performance. However, it may not be available and reliable to classify different forecasting tasks by using only meteorological weather categorization. In this paper, an unsupervised clustering-based (UC-based) solar forecasting methodology is developed for short-term (1-hour-ahead) global horizontal irradiance (GHI) forecasting. This methodology consists of three parts: GHI time series unsupervised clustering, pattern recognition, and UC-based forecasting. The daily GHI time series is first clustered by an Optimized Cross-validated ClUsteRing (OCCUR) method, which determines the optimal number of clusters and best clustering results. Then, support vector machine pattern recognition (SVM-PR) is adopted to recognize the category of a certain day using the first few hours' data in the forecasting stage. GHI forecasts are generated by the most suitable models in different clusters, which are built by a two-layer Machine learning based Multi-Model (M3) forecasting framework. The developed UC-based methodology is validated by using 1-year of data with six solar features. Numerical results show that (i) UC-based models outperform non-UC (all-in-one) models with the same M3 architecture by approximately 20%; (ii) M3-based models also outperform the single-algorithm machine learning (SAML) models by approximately 20%.

Sergiy Zhuk, Tigran Tchrakian, Albert Akhriev et al.

This paper describes a new algorithm for solar energy forecasting from a sequence of Cloud Optical Depth (COD) images. The algorithm is based on the following simple observation: the dynamics of clouds represented by COD images resembles the motion (transport) of a density in a fluid flow. This suggests that, to forecast the motion of COD images, it is sufficient to forecast the flow. The latter, in turn, can be accomplished by fitting a parametric model of the fluid flow to the COD images observed in the past. Namely, the learning phase of the algorithm is composed of the following steps: (i) given a sequence of COD images, the snapshots of the optical flow are estimated from two consecutive COD images; (ii) these snapshots are then assimilated into a Navier-Stokes Equation (NSE), i.e. an initial velocity field for NSE is selected so that the corresponding NSE' solution is as close as possible to the optical flow snapshots. The prediction phase consists of utilizing a linear transport equation, which describes the propagation of COD images in the fluid flow predicted by NSE, to estimate the future motion of the COD images. The algorithm has been tested on COD images provided by two geostationary operational environmental satellites from NOAA serving the west-hemisphere.