Sprint bdfs25 - Revision history

Darkblueb at 22:11, 1 October 2025

2025-10-01T22:11:52Z

2025-10-01T22:09:40Z

2025-10-01T21:15:53Z

2025-10-01T21:12:18Z

2025-10-01T21:03:37Z

2025-10-01T20:57:46Z

2025-09-29T02:17:50Z

2025-09-28T17:07:27Z

2025-09-28T02:53:49Z

2025-09-28T02:53:25Z

← Older revision		Revision as of 22:11, 1 October 2025
Line 61:		Line 61:
	booktitle={ICLR Workshop on Machine Learning for Remote Sensing (ML4RS)},		booktitle={ICLR Workshop on Machine Learning for Remote Sensing (ML4RS)},
	year={2024}		year={2024}
−	}	+	}

	4. '''Data availability'''		4. '''Data availability'''

@@ Line 52: / Line 52: @@
 Satlas [https://satlas-pretrain.allen.ai/ LINK] a platform for visualizing and downloading global geospatial data products generated by AI using satellite images. [https://satlas.allen.ai/map DEMO] YNews [https://news.ycombinator.com/item?id=37387556 REVIEW]
-DeepLearning and OBIA [https://arxiv.org/pdf/2408.01607? PDF]
+DeepLearning and OBIA [https://arxiv.org/pdf/2408.01607? PDF] sponsored by State Key Labs [https://en.wikipedia.org/wiki/State_Key_Laboratories LINK]
 GOOGLE_SATELLITE_EMBEDDING_V1 [https://deepmind.google/discover/blog/alphaearth-foundations-helps-map-our-planet-in-unprecedented-detail/ BLOG] [https://medium.com/google-earth/ai-powered-pixels-introducing-googles-satellite-embedding-dataset-31744c1f4650 MED] [https://developers.google.com/earth-engine/datasets/catalog/GOOGLE_SATELLITE_EMBEDDING_V1_ANNUAL LINK] related [https://christopherren.substack.com/p/embedding-fields-forever LINK]

@@ Line 108: / Line 108: @@
 '''Specialized ML models''': Traditional ML methods can outperform trendy AI approaches in remote sensing tasks.'''Public data availability''': Public datasets are essential for Earth observation research, enabling  collaboration and innovation. '''Collaboration opportunities''': The conversation likely touched upon the potential for international  collaborations across different countries and regions. '''Geospatial data infrastructure''': Standardized data formats and efficient data access mechanisms are crucial for geospatial research.
-Preparation for Big Data from Space #osgeo code sprint
+Preparation for #bids25 Big Data from Space #osgeo + Pangeo code sprint
 The participants' discussion is a preparation activity for an upcoming code sprint, where they will work together to develop innovative solutions using remote sensing and Earth observation datasets. A wiki page summarizing these ideas could be a valuable output from this collaboration.

@@ Line 33: / Line 33: @@
 PANGAEA [https://github.com/VMarsocci/pangaea-bench benchmark]  shows that specialized, not-CNN and not-ViT , machine learning models can perform better than various Foundation Models for remote sensing landuse / landcover analysis and other specific classification tasks.
 Supervised learning, XGBoost / Catboost or various Random Forest learning can perform better than ViT variations, CNN and related approaches on the six key use cases as stated by FAST-EO : weather and climate disaster analysis, methane leak detection, forest above-ground biomass change, soil property estimation, semantic land cover change detection, and monitoring the expansion of mining fields into farmlands.
 this [https://huggingface.co/ibm-esa-geospatial/TerraMind-1.0-base TerraMind] mixed model is experimental,
@@ Line 100: / Line 102: @@
 [https://openlandmap.org/ OpenLandMap]

@@ Line 32: / Line 32: @@
 PANGAEA [https://github.com/VMarsocci/pangaea-bench benchmark]  shows that specialized, not-CNN and not-ViT , machine learning models can perform better than various Foundation Models for remote sensing landuse / landcover analysis and other specific classification tasks.
-Supervised learning, XGBoost / Catboost or various Random Forest learning can perform better than ViT variations, CNN and related approaches.
+Supervised learning, XGBoost / Catboost or various Random Forest learning can perform better than ViT variations, CNN and related approaches on the six key use cases as stated by FAST-EO : weather and climate disaster analysis, methane leak detection, forest above-ground biomass change, soil property estimation, semantic land cover change detection, and monitoring the expansion of mining fields into farmlands.
 this [https://huggingface.co/ibm-esa-geospatial/TerraMind-1.0-base TerraMind] mixed model is experimental,

@@ Line 75: / Line 75: @@
 The project involves a consortium of partners including Forschungszentrum Jülich, KP Labs, and IBM Research, who are collaborating on six key use cases: weather and climate disaster analysis, methane leak detection, forest above-ground biomass change, soil property estimation, semantic land cover change detection, and monitoring the expansion of mining fields into farmlands. The project is committed to open science, planning to release model weights, configurations, datasets, and source code under a free and permissive Apache-2 license, accessible via platforms like GitHub, HuggingFace, and the SpatioTemporal Asset Catalog (STAC).
-Other public training [https://x-ytong.github.io/project/Five-Billion-Pixels.html DATA] for China interior, by Prof. Dr. Xiou xiang Zhu .. who is very much in Germany and is the boss of the department with the `torchGeo` guy
+Other public training [https://x-ytong.github.io/project/Five-Billion-Pixels.html DATA] for China interior, by Prof. Dr. Xiou xiang Zhu .. who is very much in Germany and is the boss of the department with the `torchGeo` project founder
 gdal containers [https://github.com/OSGeo/gdal/pkgs/container/gdal LINK]

← Older revision		Revision as of 02:17, 29 September 2025
Line 14:		Line 14:

	TerraBytes Canada [https://terrabytes-workshop.github.io/ LINK]		TerraBytes Canada [https://terrabytes-workshop.github.io/ LINK]
		+
		+	Geometa Lab [https://www.giswiki.ch/Agenda LINK]

@@ Line 50: / Line 50: @@
 DeepLearning and OBIA [https://arxiv.org/pdf/2408.01607? PDF]
+GOOGLE_SATELLITE_EMBEDDING_V1 [https://deepmind.google/discover/blog/alphaearth-foundations-helps-map-our-planet-in-unprecedented-detail/ BLOG] [https://medium.com/google-earth/ai-powered-pixels-introducing-googles-satellite-embedding-dataset-31744c1f4650 MED] [https://developers.google.com/earth-engine/datasets/catalog/GOOGLE_SATELLITE_EMBEDDING_V1_ANNUAL LINK] related [https://christopherren.substack.com/p/embedding-fields-forever LINK]
   @inproceedings{brown2024learned,
@@ Line 63: / Line 58: @@
    year={2024}
+}
 Global Forest Watch edu [https://glad.umd.edu/projects/global-forest-watch LINK]

← Older revision		Revision as of 02:53, 28 September 2025
Line 48:		Line 48:
	Satlas [https://satlas-pretrain.allen.ai/ LINK] a platform for visualizing and downloading global geospatial data products generated by AI using satellite images. [https://satlas.allen.ai/map DEMO] YNews [https://news.ycombinator.com/item?id=37387556 REVIEW]		Satlas [https://satlas-pretrain.allen.ai/ LINK] a platform for visualizing and downloading global geospatial data products generated by AI using satellite images. [https://satlas.allen.ai/map DEMO] YNews [https://news.ycombinator.com/item?id=37387556 REVIEW]

		+	DeepLearning and OBIA [https://arxiv.org/pdf/2408.01607? PDF]

−	~~DeepLearning and OBIA [https://arxiv.org/pdf/2408.01607? PDF]~~

	4. '''Data availability'''		4. '''Data availability'''