various

Author: robmarkcole

README.md

@@ -387,6 +387,8 @@ Note that deforestation detection may be treated as a segmentation task or a cha
 
 - [IBM BlueSky Challenge - ZeroFlood](https://github.com/oroikono/IBM-BlueSky-Challenge-ZeroFlood)
 
+- [OmniWaterMask-training](https://github.com/DPIRD-DMA/OmniWaterMask-training) -> Training code for the deep learning model used in [OmniWaterMask](https://github.com/DPIRD-DMA/OmniWaterMask) - a Python library for detecting water bodies in satellite and aerial imagery.
+
 ### Segmentation - Fire, smoke & burn areas
 
 - [SatelliteVu-AWS-Disaster-Response-Hackathon](https://github.com/SatelliteVu/SatelliteVu-AWS-Disaster-Response-Hackathon) -> fire spread prediction using classical ML & deep learning
@@ -1418,6 +1420,8 @@ A variety of techniques can be used to count animals, including object detection
 
 - [HerdNet](https://github.com/Alexandre-Delplanque/HerdNet) -> From Crowd to Herd Counting: How to Precisely Detect and Count African Mammals using Aerial Imagery and Deep Learning?
 
+- [sat-rhino](https://github.com/sat-rhino/sat-rhino) -> evaluating a YOLOv12 model, plus tools for generating synthetic data in Blender
+
 ### Object detection - Miscellaneous
 
 - [Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review](https://www.mdpi.com/2072-4292/12/10/1667)
@@ -1568,6 +1572,8 @@ Regression in remote sensing involves predicting continuous variables such as wi
 
 - [TREASURE-NET](https://github.com/Global-Earth-Observation/threasure-net) -> Super-Resolved Canopy Height Mapping from Sentinel-2 Time Series Using LiDAR HD Reference Data across Metropolitan France
 
+- [Seabed-Net](https://github.com/pagraf/Seabed-Net) -> A multi-task network for joint bathymetry and pixel-based seabed classification from remote sensing imagery in shallow waters, uses [MagicBathyNet](https://www.magicbathy.eu/magicbathynet.html) dataset
+
 #
 ## Cloud detection & removal
 
@@ -2085,6 +2091,8 @@ The analysis of time series observations in remote sensing data has numerous app
 
 - [CNN-LSTM_for_DSM](https://github.com/leizhang-geo/CNN-LSTM_for_DSM) -> A CNN-LSTM model for soil organic carbon content prediction with long time series of MODIS-based phenological variables
 
+- [rice-irrigation-mapping-s1s2](https://github.com/microsoft/rice-irrigation-mapping-s1s2) -> Mapping rice irrigation using Sentinel-1 and Sentinel-2 data
+
 #
 ## Crop classification
 
@@ -2696,6 +2704,8 @@ Data fusion is a technique for combining information from different sources such
 
 - [TIF: Time-series-based Image Fusion](https://github.com/GERSL/TIF) -> produce 10 m Harmonized Landsat and Sentinel-2 (HLS) data by fusing 30 m Landsat 8-9 and 10 m Sentinel-2 A/B time series
 
+- [AnytimeFormer](https://github.com/tangkai-RS/AnytimeFormer) -> Fusing irregular and asynchronous SAR-optical time series to reconstruct reflectance at any given time
+
 #
 ## Generative networks
 
@@ -3526,6 +3536,8 @@ SAR (synthetic aperture radar) is used to detect and measure the properties of o
 
 - [SAM3SAR: Ship Segmentation in SAR with SAM3‑UNet](https://github.com/edwardarchaeology/SAR_Segmentation_with_SAM3_UNET)
 
+- [SARMSSD](https://github.com/buyukkanber/SARMSSD) -> Impact of Data Enhancement Methods on Ship Detection Using YOLO11 in SAR Imagery
+
 #
 ## NDVI - vegetation index
 
@@ -3625,6 +3637,8 @@ Training data can be hard to acquire, particularly for rare events such as chang
 
 - [Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision](https://github.com/humansensinglab/AGenDA) -> Leverage synthetic data generated by Stable Diffusion to enhance cross-domain object detection in aerial imagery.
 
+- [VectorSynth](https://github.com/mvrl/VectorSynth) -> a suite of models for synthesizing satellite images with global style and text-driven layout control
+
 # 
 ## Explainable Ai (XAI)
 Explainable AI (XAI) is a field of artificial intelligence that focuses on developing methods and techniques to make the decision-making process of AI systems more transparent and understandable to humans. XAI aims to provide insights into how AI models arrive at their predictions or decisions, allowing users to trust and interpret the results effectively. This is particularly important in remote sensing applications where understanding the rationale behind AI-driven insights can be crucial for decision-making in areas such as environmental monitoring, disaster response, and land use planning.
@@ -3737,5 +3751,7 @@ Explainable AI (XAI) is a field of artificial intelligence that focuses on devel
 
 - [LandSegmenter](https://github.com/zhu-xlab/LandSegmenter) -> Towards a Flexible Foundation Model for Land Use and Land Cover Mapping
 
+- [GeoLink_NeurIPS2025](https://github.com/bailubin/GeoLink_NeurIPS2025) -> GeoLink is a multimodal framework that empowers remote sensing foundation models by integrating OpenStreetMap (OSM) data in both pretraining stage and downstream tasks
+
 ----
 - *Logo created with* [*Brandmark*](https://app.brandmark.io/v3/)