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{Anonymity Link}.
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.
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.
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.
Vision foundation models are a new frontier in GeoAI research 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 popular 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 impressive transferability of the Prithvi model, highlighting its performance advantages in segmenting flooded areas in previously unseen regions. The findings also suggest 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.
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.
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.
This article investigates the challenge of achieving functional tool-use grasping with high-DoF anthropomorphic hands, with the aim of enabling anthropomorphic hands to perform tasks that require human-like manipulation and tool-use. However, accomplishing human-like grasping in real robots present many challenges, including obtaining diverse functional grasps for a wide variety of objects, handling generalization ability for kinematically diverse robot hands and precisely completing object shapes from a single-view perception. To tackle these challenges, we propose a six-step grasp synthesis algorithm based on fine-grained contact modeling that generates physically plausible and human-like functional grasps for category-level objects with minimal human demonstrations. With the contact-based optimization and learned dense shape correspondence, the proposed algorithm is adaptable to various objects in same category and a board range of robot hand models. To further demonstrate the robustness of the framework, over 10K functional grasps are synthesized to train our neural network, named DexFG-Net, which generates diverse sets of human-like functional grasps based on the reconstructed object model produced by a shape completion module. The proposed framework is extensively validated in simulation and on a real robot platform. Simulation experiments demonstrate that our method outperforms baseline methods by a large margin in terms of grasp functionality and success rate. Real robot experiments show that our method achieved an overall success rate of 79\% and 68\% for tool-use grasp on 3-D printed and real test objects, respectively, using a 5-Finger Schunk Hand. The experimental results indicate a step towards human-like grasping with anthropomorphic hands.