CloudLULC-Net is an end-to-end heterogeneous SAR-optical fusion network for LULC mapping under cloud contamination that achieves 86.60% OA, 83.29% F1, and 73.51% mIoU on a new global benchmark of 40,223 samples.
hub
1396–1399
12 Pith papers cite this work, alongside 310 external citations. Polarity classification is still indexing.
12
Pith papers citing it
310
external citations · external index
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
EO-Gym supplies an executable multimodal environment and 9k-trajectory benchmark that turns Earth Observation into a tool-using, multi-step reasoning task, revealing that current VLMs struggle on temporal and cross-sensor workflows while fine-tuning lifts Pass@3 from 0.49 to 0.74.
SpectralEarth-FM is a multisensor hierarchical transformer pretrained on a 40TB co-located HSI-MSI-SAR dataset using a JEPA-style objective and reports state-of-the-art results on hyperspectral and standard EO benchmarks.
Prompt-generated image-mask pairs, mixed with real UAV imagery at a 40:60 ratio, lift forest-regeneration segmentation by >15 F1 points over supervised baselines and sharply improve rare-species F1.
M-CaStLe generalizes local stencil-based causal discovery to the multivariate case and decomposes resulting graphs into reaction and spatial components for interpretation in space-time gridded data.
Standardized pretraining and evaluation of geospatial multimodal foundation models on GEOBench reveals design trade-offs in flexibility, modality alignment, and task performance.
Adding MAR climate-model features plus a multi-branch GraphSAGE/temporal-convolution design with adaptive fusion reduces deep-ice-layer thickness RMSE by 21.01% over a no-knowledge multi-branch baseline on the SRED Greenland dataset.
Proposes ISensD and ESensI methods to increase robustness of multi-sensor EO models to missing sensors, with experiments on three temporal datasets showing ensemble models are most robust.
Year-wise cross-validation across ten ML algorithms on Harmonized Landsat-Sentinel imagery shows SVMs achieve mean F1 of 0.74 for almonds in California and 0.59 for corn in Iowa by early June in unseen validation years.
Deployment-aligned low-precision NAS recovers about two-thirds of the accuracy drop from post-training quantization, achieving 0.826 mIoU on-device for a 95k-parameter model on Intel Movidius Myriad X without added complexity.
TerraQ is a spatiotemporal question-answering engine for satellite image archives that processes natural language requests involving image metadata and knowledge base entities.
Tensor networks developed for quantum states are reviewed as tools for machine learning models, with assessment of their potential computational, explanatory, and privacy advantages alongside remaining challenges.
citing papers explorer
-
Heterogeneous SAR-optical fusion for near-real-time land use and land cover mapping under cloud contamination: A novel framework and global benchmark dataset
CloudLULC-Net is an end-to-end heterogeneous SAR-optical fusion network for LULC mapping under cloud contamination that achieves 86.60% OA, 83.29% F1, and 73.51% mIoU on a new global benchmark of 40,223 samples.
-
EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents
EO-Gym supplies an executable multimodal environment and 9k-trajectory benchmark that turns Earth Observation into a tool-using, multi-step reasoning task, revealing that current VLMs struggle on temporal and cross-sensor workflows while fine-tuning lifts Pass@3 from 0.49 to 0.74.
-
SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretraining
SpectralEarth-FM is a multisensor hierarchical transformer pretrained on a 40TB co-located HSI-MSI-SAR dataset using a JEPA-style objective and reports state-of-the-art results on hyperspectral and standard EO benchmarks.
-
Leveraging Image Generators to Address Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping
Prompt-generated image-mask pairs, mixed with real UAV imagery at a 40:60 ratio, lift forest-regeneration segmentation by >15 F1 points over supervised baselines and sharply improve rare-species F1.
-
M-CaStLe: Uncovering Local Causal Structures in Multivariate Space-Time Gridded Data
M-CaStLe generalizes local stencil-based causal discovery to the multivariate case and decomposes resulting graphs into reaction and spatial components for interpretation in space-time gridded data.
-
Emerging Flexible Designs for Geospatial Multimodal Foundation Models
Standardized pretraining and evaluation of geospatial multimodal foundation models on GEOBench reveals design trade-offs in flexibility, modality alignment, and task performance.
-
K-STEMIT: Knowledge-Informed Spatio-Temporal Efficient Multi-Branch Graph Neural Network for Subsurface Stratigraphy Thickness Estimation from Radar Data
Adding MAR climate-model features plus a multi-branch GraphSAGE/temporal-convolution design with adaptive fusion reduces deep-ice-layer thickness RMSE by 21.01% over a no-knowledge multi-branch baseline on the SRED Greenland dataset.
-
Increasing the Robustness of Model Predictions to Missing Sensors in Earth Observation
Proposes ISensD and ESensI methods to increase robustness of multi-sensor EO models to missing sensors, with experiments on three temporal datasets showing ensemble models are most robust.
-
Intercomparison of Machine Learning Algorithms for Remote Sensing-based In-season Crop Mapping
Year-wise cross-validation across ten ML algorithms on Harmonized Landsat-Sentinel imagery shows SVMs achieve mean F1 of 0.74 for almonds in California and 0.59 for corn in Iowa by early June in unseen validation years.
-
Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI
Deployment-aligned low-precision NAS recovers about two-thirds of the accuracy drop from post-training quantization, achieving 0.826 mIoU on-device for a 95k-parameter model on Intel Movidius Myriad X without added complexity.
-
TerraQ: Spatiotemporal Question-Answering on Satellite Image Archives
TerraQ is a spatiotemporal question-answering engine for satellite image archives that processes natural language requests involving image metadata and knowledge base entities.
-
Quantum-inspired tensor networks in machine learning models
Tensor networks developed for quantum states are reviewed as tools for machine learning models, with assessment of their potential computational, explanatory, and privacy advantages alongside remaining challenges.