gis software developers

Abstract: Source-only domain generalization (DG) for remote sensing semantic segmentation seeks reliable predictions in unseen domains without target-domain data during training. Although vision foundation models offer transferable knowledge, category recognition remains sensitive to source-specific visual cues, while task-specific adaptation may weaken pretrained transferability. We propose ASCoR, an asymmetric semantic-spatial framework built on SAM3. Its text-conditioned semantic branch uses class-name prompts to provide explicit category guidance. Probe-Once Dynamic Adaptive LoRA distributes a fixed adaptation budget across encoder blocks to limit source-specific specialization. A complementary task-specific dense branch learns multi-scale spatial representations using a separate frozen SAM3 image encoder. A lightweight reliability router integrates the two branches through bounded spatial correction based on local prediction reliability. All components are trained using source-domain supervision only. Experiments on the ISPRS, LoveDA, and OpenEarthMap benchmarks cover nine cross-domain transfers. ASCoR achieves a state-of-the-art mean IoU of 68.61% across six ISPRS transfers, outperforming the previous best method by 2.69 percentage points. It also achieves the best results on all three LoveDA/OpenEarthMap transfers, with 59.07%, 47.95%, and 49.38% mIoU on Rural-to-Urban, Urban-to-Rural, and Urban-to-OpenEarthMap, respectively. Ablation studies, feature visualizations, and spatial reliability analyses support the effectiveness and complementarity of the proposed components. Code: https://github.com/WangZitong42/ASCoR.

Abstract: We present a deterministic algorithm that approximates the Fréchet distance between two polygonal curves in $\mathbb{R}^d$ with $n$ and $m$ vertices within a constant factor in $O((m+n)^{1+\varepsilon})$ time, for every fixed $\varepsilon>0$ and fixed dimension $d$. The approximation factor depends only on $\varepsilon$ and $d$. No assumption on the input curves is needed, and the algorithm also reports a matching certifying the approximation. The same result holds for the discrete Fréchet distance. Our result extends the line of work initiated by Cheng, Huang, and Zhang (2025), who gave the first constant-factor approximation in strongly subquadratic time, to near-linear time. For two $n$-vertex curves, the best previous running time was $\widetilde{O}(n^{5/3})$, due to van der Horst and Ophelders (2026). Our algorithm bootstraps between two primitives: a data structure that preprocesses a single curve for comparing any two of its subcurves, and a query procedure that compares subcurves of two different curves. Given the data structure for one curve, we compare it with another curve using a surrogate assembled from subcurves of the former. The surrogate is shared by all possible starting points of a matching. Conversely, faster queries make the next data structure cheaper to build. After a number of rounds that depends only on $\varepsilon$, both preprocessing and query time are $O((m+n)^{1+\varepsilon})$. To make each round's output reusable by the next, we compactly summarize how matchings can enter and leave a pair of subcurves. These summaries can be applied to different starting points and retain the information needed to report the matchings.

Abstract: The emergence of large language models (LLMs) and large multimodal models (LMMs) has enabled a new class of agentic systems capable of integrating natural language understanding with tool-based execution. In geographic information systems (GIS), this shift is transforming traditional, expert-driven workflows into semiautonomous systems that can interpret user intent, construct spatial workflows, and execute geospatial analysis tasks. However, existing approaches remain limited by fragmented integration of reasoning, execution, and evaluation, particularly in complex, real-world environments. This study synthesizes recent advances in agentic GIS frameworks, benchmarks, and surveys to identify limitations in spatial reasoning, execution robustness, validation, governance, and evaluation. Building on these insights, it introduces ANASSA (Autonomous Neural Agents for Spatial Systems Architecture), an agentic AI orchestration framework that integrates structured spatial reasoning, multi-agent workflow orchestration, execution feedback, authoritative spatial validation, provenance, uncertainty handling, and human decision authority within a unified system design. The contribution is an architecture-level specification: eleven components across four layers, a six-step Geospatial AI Cognitive Loop, cross-component contracts, and governance mechanisms intended to make agentic geospatial workflows traceable, reproducible, and accountable. Empirical performance evaluation is reserved for implementation and deployment studies.