Sizhe Wang

Sizhe Wang, Ziqi Xu, Claire Najjuuko et al.

Clinical language models (LMs) are increasingly applied to support clinical risk prediction from free-text notes, yet their uncertainty estimates often remain poorly calibrated and clinically unreliable. In this work, we propose Clinical Uncertainty Risk Alignment (CURA), a framework that aligns clinical LM-based risk estimates and uncertainty with both individual error likelihoods and cohort-level ambiguities. CURA first fine-tunes domain-specific clinical LMs to obtain task-adapted patient embeddings, and then performs uncertainty fine-tuning of a multi-head classifier using a bi-level uncertainty objective. Specifically, an individual-level calibration term aligns predictive uncertainty with each patient's likelihood of error, while a cohort-aware regularizer pulls risk estimates toward event rates in their local neighborhoods in the embedding space and places extra weight on ambiguous cohorts near the decision boundary. We further show that this cohort-aware term can be interpreted as a cross-entropy loss with neighborhood-informed soft labels, providing a label-smoothing view of our method. Extensive experiments on MIMIC-IV clinical risk prediction tasks across various clinical LMs show that CURA consistently improves calibration metrics without substantially compromising discrimination. Further analysis illustrates that CURA reduces overconfident false reassurance and yields more trustworthy uncertainty estimates for downstream clinical decision support.

Wenwen Li, Chia-Yu Hsu, Sizhe Wang et al.

This paper introduces a real-time GeoAI workflow for large-scale image analysis and the segmentation of Arctic permafrost features at a fine-granularity. Very high-resolution (0.5m) commercial imagery is used in this analysis. To achieve real-time prediction, our workflow employs a lightweight, deep learning-based instance segmentation model, SparseInst, which introduces and uses Instance Activation Maps to accurately locate the position of objects within the image scene. Experimental results show that the model can achieve better accuracy of prediction at a much faster inference speed than the popular Mask-RCNN model.

Wenwen Li, Hyunho Lee, Sizhe Wang et al.

Vision foundation models are a new frontier in Geospatial Artificial Intelligence (GeoAI), an interdisciplinary research area that applies and extends AI for geospatial problem solving and geographic knowledge discovery, because of their potential to enable powerful image analysis by learning and extracting important image features from vast amounts of geospatial data. This paper evaluates the performance of the first-of-its-kind geospatial foundation model, IBM-NASA's Prithvi, to support a crucial geospatial analysis task: flood inundation mapping. This model is compared with convolutional neural network and vision transformer-based architectures in terms of mapping accuracy for flooded areas. A benchmark dataset, Sen1Floods11, is used in the experiments, and the models' predictability, generalizability, and transferability are evaluated based on both a test dataset and a dataset that is completely unseen by the model. Results show the good transferability of the Prithvi model, highlighting its performance advantages in segmenting flooded areas in previously unseen regions. The findings also indicate areas for improvement for the Prithvi model in terms of adopting multi-scale representation learning, developing more end-to-end pipelines for high-level image analysis tasks, and offering more flexibility in terms of input data bands.

Yongqi Tong, Yifan Wang, Dawei Li et al.

Chain-of-Thought(CoT) prompting and its variants explore equipping large language models (LLMs) with high-level reasoning abilities by emulating human-like linear cognition and logic. However, the human mind is complicated and mixed with both linear and nonlinear thinking. In this work, we propose \textbf{I}nferential \textbf{E}xclusion \textbf{P}rompting (IEP), a novel prompting that combines the principles of elimination and inference in order to guide LLMs to think non-linearly. IEP guides LLMs to plan and then utilize Natural Language Inference (NLI) to deduce each possible solution's entailment relation with context, commonsense, or facts, therefore yielding a broader perspective by thinking back for inferring. This forward planning and backward eliminating process allows IEP to better simulate the complex human thinking processes compared to other CoT-based methods, which only reflect linear cognitive processes. We conducted a series of empirical studies and have corroborated that IEP consistently outperforms CoT across various tasks. Additionally, we observe that integrating IEP and CoT further improves the LLMs' performance on certain tasks, highlighting the necessity of equipping LLMs with mixed logic processes. Moreover, to better evaluate comprehensive features inherent in human logic, we introduce \textbf{M}ental-\textbf{A}bility \textbf{R}easoning \textbf{B}enchmark (MARB). The benchmark comprises six novel subtasks with a total of 9,115 questions, among which 1,685 are developed with hand-crafted rationale references. We believe both \textsc{IEP} and \textsc{MARB} can serve as a promising direction for unveiling LLMs' logic and verbal reasoning abilities and drive further advancements. \textsc{MARB} will be available at ~\texttt{anonymity link} soon.

Yongqi Tong, Dawei Li, Sizhe Wang et al.

Recent works have shown the benefits to LLMs from fine-tuning golden-standard Chain-of-Thought (CoT) rationales or using them as correct examples in few-shot prompting. While humans can indeed imitate correct examples, learning from our mistakes is another vital aspect of human cognition. Hence, a question naturally arises: \textit{can LLMs learn and benefit from their mistakes, especially for their reasoning? } This study investigates this problem from both the prompting and model-tuning perspectives. We begin by introducing \textsc{CoTErrorSet}, a new benchmark with 609,432 questions, each designed with both correct and error references, and demonstrating the types and reasons for making such mistakes. To explore the effectiveness of those mistakes, we design two methods: (1) \textbf{Self-rethinking} prompting guides LLMs to rethink whether they have made similar previous mistakes; and (2) \textbf{Mistake tuning} involves finetuning models in both correct and incorrect reasoning domains, rather than only tuning models to learn ground truth in traditional methodology. We conduct a series of experiments to prove LLMs can obtain benefits from mistakes in both directions. Our two methods offer potentially cost-effective strategies by leveraging errors to enhance reasoning capabilities, which costs significantly less than creating meticulously hand-crafted golden references. We ultimately make a thorough analysis of the reasons behind LLMs' errors, which provides directions that future research needs to overcome. \textsc{CoTErrorSet} will be published soon on \texttt{\url{https://github.com/YookiTong/Learn-from-Mistakes-CotErrorSet}}.

Wenwen Li, Sizhe Wang, Hyunho Lee et al.

Landslides cause severe damage to lives, infrastructure, and the environment, making accurate and timely mapping essential for disaster preparedness and response. However, conventional deep learning models often struggle when applied across different sensors, regions, or under conditions of limited training data. To address these challenges, we present a three-axis analytical framework of sensor, label, and domain for adapting geospatial foundation models (GeoFMs), focusing on Prithvi-EO-2.0 for landslide mapping. Through a series of experiments, we show that it consistently outperforms task-specific CNNs (U-Net, U-Net++), vision transformers (Segformer, SwinV2-B), and other GeoFMs (TerraMind, SatMAE). The model, built on global pretraining, self-supervision, and adaptable fine-tuning, proved resilient to spectral variation, maintained accuracy under label scarcity, and generalized more reliably across diverse datasets and geographic settings. Alongside these strengths, we also highlight remaining challenges such as computational cost and the limited availability of reusable AI-ready training data for landslide research. Overall, our study positions GeoFMs as a step toward more robust and scalable approaches for landslide risk reduction and environmental monitoring.

Daniela Szwarcman, Sujit Roy, Paolo Fraccaro et al.

This technical report presents Prithvi-EO-2.0, a new geospatial foundation model that offers significant improvements over its predecessor, Prithvi-EO-1.0. Trained on 4.2M global time series samples from NASA's Harmonized Landsat and Sentinel-2 data archive at 30m resolution, the new 300M and 600M parameter models incorporate temporal and location embeddings for enhanced performance across various geospatial tasks. Through extensive benchmarking with GEO-Bench, the 600M version outperforms the previous Prithvi-EO model by 8\% across a range of tasks. It also outperforms six other geospatial foundation models when benchmarked on remote sensing tasks from different domains and resolutions (i.e. from 0.1m to 15m). The results demonstrate the versatility of the model in both classical earth observation and high-resolution applications. Early involvement of end-users and subject matter experts (SMEs) are among the key factors that contributed to the project's success. In particular, SME involvement allowed for constant feedback on model and dataset design, as well as successful customization for diverse SME-led applications in disaster response, land use and crop mapping, and ecosystem dynamics monitoring. Prithvi-EO-2.0 is available on Hugging Face and IBM terratorch, with additional resources on GitHub. The project exemplifies the Trusted Open Science approach embraced by all involved organizations.

Yongqi Tong, Sizhe Wang, Dawei Li et al.

While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts. However, this reliance on fully-supervised annotations poses scalability challenges, particularly as models and data requirements grow. To mitigate this, we explore the potential of enhancing LLMs' reasoning abilities with minimal human supervision. In this work, we introduce self-reinforcement, which begins with Supervised Fine-Tuning (SFT) of the model using a small collection of annotated questions. Then it iteratively improves LLMs by learning from the differences in responses from the SFT and unfinetuned models on unlabeled questions. Our approach provides an efficient approach without relying heavily on extensive human-annotated explanations. However, current reasoning benchmarks typically only include golden-reference answers or rationales. Therefore, we present \textsc{PuzzleBen}, a weakly supervised benchmark that comprises 25,147 complex questions, answers, and human-generated rationales across various domains, such as brainteasers, puzzles, riddles, parajumbles, and critical reasoning tasks. A unique aspect of our dataset is the inclusion of 10,000 unannotated questions, enabling us to explore utilizing fewer supersized data to boost LLMs' inference capabilities. Our experiments underscore the significance of \textsc{PuzzleBen}, as well as the effectiveness of our methodology as a promising direction in future endeavors. Our dataset and code will be published soon on \texttt{Anonymity Link}.

Wenwen Li, Hu Shao, Sizhe Wang et al.

Big earth science data offers the scientific community great opportunities. Many more studies at large-scales, over long-terms and at high resolution can now be conducted using the rich information collected by remote sensing satellites, ground-based sensor networks, and even social media input. However, the hundreds of terabytes of information collected and compiled on an hourly basis by NASA and other government agencies present a significant challenge for atmospheric scientists seeking to improve the understanding of the Earth atmospheric system. These challenges include effective discovery, organization, analysis and visualization of large amounts of data. This paper reports the outcomes of an NSF-funded project that developed a geospatial cyberinfrastructure -- the A2CI (Atmospheric Analysis Cyberinfrastructure) -- to support atmospheric research. We first introduce the service-oriented system framework then describe in detail the implementation of the data discovery module, data management module, data integration module, data analysis and visualization modules following the cloud computing principles-Data-as-a-Service, Software-as-a-Service, Platform-as-a-Service and Infrastructure-as-a-Service. We demonstrate the graphic user interface by performing an analysis between Sea Surface Temperature and the intensity of tropical storms in the North Atlantic and Pacific oceans. We expect this work to contribute to the technical advancement of cyberinfrastructure research as well as to the development of an online, collaborative scientific analysis system for atmospheric science.

Cogan Shimizu, Shirly Stephe, Adrita Barua et al.

KnowWhereGraph is one of the largest fully publicly available geospatial knowledge graphs. It includes data from 30 layers on natural hazards (e.g., hurricanes, wildfires), climate variables (e.g., air temperature, precipitation), soil properties, crop and land-cover types, demographics, and human health, various place and region identifiers, among other themes. These have been leveraged through the graph by a variety of applications to address challenges in food security and agricultural supply chains; sustainability related to soil conservation practices and farm labor; and delivery of emergency humanitarian aid following a disaster. In this paper, we introduce the ontology that acts as the schema for KnowWhereGraph. This broad overview provides insight into the requirements and design specifications for the graph and its schema, including the development methodology (modular ontology modeling) and the resources utilized to implement, materialize, and deploy KnowWhereGraph with its end-user interfaces and public query SPARQL endpoint.

Hengyuan Zhang, Chenming Shang, Sizhe Wang et al.

Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the dominant language (e.g., English) and non-dominant ones due to the imbalance of training data across languages. To further enhance the performance of non-dominant languages, we propose ShifCon, a Shift-based multilingual Contrastive framework that aligns the internal forward process of other languages toward that of the dominant one. Specifically, it shifts the representations of non-dominant languages into the dominant language subspace, allowing them to access relatively rich information encoded in the model parameters. The enriched representations are then shifted back into their original language subspace before generation. Moreover, we introduce a subspace distance metric to pinpoint the optimal layer area for shifting representations and employ multilingual contrastive learning to further enhance the alignment of representations within this area. Experiments demonstrate that our ShifCon framework significantly enhances the performance of non-dominant languages, particularly for low-resource ones. Further analysis offers extra insights to verify the effectiveness of ShifCon and propel future research.

Wenwen Li, Chia-Yu Hsu, Sizhe Wang et al.

This paper assesses trending AI foundation models, especially emerging computer vision foundation models and their performance in natural landscape feature segmentation. While the term foundation model has quickly garnered interest from the geospatial domain, its definition remains vague. Hence, this paper will first introduce AI foundation models and their defining characteristics. Built upon the tremendous success achieved by Large Language Models (LLMs) as the foundation models for language tasks, this paper discusses the challenges of building foundation models for geospatial artificial intelligence (GeoAI) vision tasks. To evaluate the performance of large AI vision models, especially Meta's Segment Anything Model (SAM), we implemented different instance segmentation pipelines that minimize the changes to SAM to leverage its power as a foundation model. A series of prompt strategies was developed to test SAM's performance regarding its theoretical upper bound of predictive accuracy, zero-shot performance, and domain adaptability through fine-tuning. The analysis used two permafrost feature datasets, ice-wedge polygons and retrogressive thaw slumps because (1) these landform features are more challenging to segment than manmade features due to their complicated formation mechanisms, diverse forms, and vague boundaries; (2) their presence and changes are important indicators for Arctic warming and climate change. The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping. The spatial and domain generalizability of this finding is further validated using a more general dataset EuroCrop for agricultural field mapping. Finally, we discuss future research directions that strengthen SAM's applicability in challenging geospatial domains.

Yuanyuan Tian, Wenwen Li, Sizhe Wang et al.

Initiated by the University Consortium of Geographic Information Science (UCGIS), GIS&T Body of Knowledge (BoK) is a community-driven endeavor to define, develop, and document geospatial topics related to geographic information science and technologies (GIS&T). In recent years, GIS&T BoK has undergone rigorous development in terms of its topic re-organization and content updating, resulting in a new digital version of the project. While the BoK topics provide useful materials for researchers and students to learn about GIS, the semantic relationships among the topics, such as semantic similarity, should also be identified so that a better and automated topic navigation can be achieved. Currently, the related topics are either defined manually by editors or authors, which may result in an incomplete assessment of topic relationship. To address this challenge, our research evaluates the effectiveness of multiple natural language processing (NLP) techniques in extracting semantics from text, including both deep neural networks and traditional machine learning approaches. Besides, a novel text summarization - KACERS (Keyword-Aware Cross-Encoder-Ranking Summarizer) - is proposed to generate a semantic summary of scientific publications. By identifying the semantic linkages among key topics, this work provides guidance for future development and content organization of the GIS&T BoK project. It also offers a new perspective on the use of machine learning techniques for analyzing scientific publications, and demonstrate the potential of KACERS summarizer in semantic understanding of long text documents.