Climate Data Resources

Brown University Library

Open Data Resources, includes data in categories "Earth and Geoscience" and "Environment." 

Academic Data Sets

• CloudCase:  A large-scale dataset and baseline for forecasting clouds 

• WildfireDB: A Spatio-Temporal Dataset Combining Wildfire Occurrence with Relevant Covariates

• Grass Clover Data Set 

• Plant Seedling Classification

• Leaf counting   

• Leaf Classification 

• Zebrafish tracking data

• Bark classification

• Plant phenotypes

• FOWD:  Free Ocean Wave Dataset for Data Mining and Machine Learning

• Stanford Earthquake Data Set 

• Harvard Dataverse: a repository for research data

• Rhode Island Data Discovery Center

Other Data Sets or Repositories

• ClimateNet Datasets (NERSC) 

• OpenML 

• Google Dataset Search: search engine for data

• Google Earth Engine Data Sets: a planetary-scale platform for Earth Science data and analysis

• Registry of Open Data on AWS: open geospatial data 

• NASA Earth Science Data 

• National Centers for Environmental Information - Data Access: climate and weather data  (NOAA)

  • Paleoclimatology, Marine/Ocean, Model data, etc.

• xBD Dataset: annotated high-resolution satellite imagery for building damage assessment

• SpaceNet Challenge Datasets

• iWildCam 2020 Competition: camera trap images

• DeepWeeds: a multi-class weed species image classification data set  

• xView: aerial imagery 

• AI for Good Foundation (data available for some projects)

• TensorFlow Datasets: ready-to-use datasets for machine learning in Python (e.g. BigEarthNet, EuroSAT)

• Earth System Science Data: data publishing journal 

• Data.gov: US government's Open Data 

• USGS Science Data Catalog 

• COVID + Atmosphere data sets (Caltech)

• Xeno-canto: Bird Call repository 

• Atmospheric Radiation Measurement (ARM) Data 

• Gridded Climate Data Sets (Physical Sciences Laboratory, NOAA)

• Geothermal Data Repository

Added for Spring 2022

• EarthNet Challenge 2021

• Weather4Cast:  Multi-sensor Weather Forecast Competition

• HumAID: human-annotated disaster incidents data from Twitter  [paper]  [dataset]

• CrisisBench: crisis-related social media datasets for humanitarian information processing  [paper]  [dataset]

• WILDS datasets: distribution shift in the wild

• CropHarvest: open source remote sensing dataset for agriculture

• Radiant MLHub: open library for  Earth observation machine learning

• ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models

• EaDAR Lab vertical land motion datasets

• Argo Float Ocean Data

• SECOORA Data Portal: Centralized access to Southeast U.S. coastal and ocean data

• LILA Data Sets: Biology and Conservation

• EuroCrops: A Pan-European Dataset for Time Series Crop Type Classification [arXiv]

• ACM Energy Systems and Informatics:  Resources - Datasets

• OceanOPS:  Global Ocean Observing Systems Coordination framework

• SSL4EO-S12:  Multi-modal, multi-temporal dataset for unsupervised/self-supervised pre-training in Earth observation

• Data Underground: Subsurface/geophysical datasets

• TALLO: a global tree allometry and crown architecture database

• Caltech Fish Counting Dataset

Added in 2023  (for EEPS-DATA 1720 or 1340)

• ReaLSAT, A global dataset of reservoir and lake surface area variations 

• Dynamic World, Near real-time global 10m land use land cover mapping

• ClimateBench v1.0: A Benchmark for Data-Driven Climate Projections

• NADBenchmarks: a compilation of Benchmark Datasets for ML Tasks related to Natural Disasters

• NICFI Satellite Data Program:  access to Planet's high-resolution, analysis-ready mosaics of the world’s tropics.

• CaFFE: a benchmark dataset and methodology for automatic glacier calving fron extraction for SAR imagery. 

• WorldStrat: open high-resolution satellite imagery with application to super-resolution

• ENS-10: a dataset for post-processing ensemble weather forecasts

• Change Event dataset: for discovery from spatio-temporal remote sensing imagery

• PDEBench: an extensive benchmark for scientific machine learning

• xView3-SAR: Detecting dark fishing activity using SAR imagery

• Caravan: a global community dataset for large-sample hydrology 

• DoriaNet: a visual dataset from Hurricane Dorian for post-disaster building damage assessment

• CSU Synthetic Attribution Benchmark Dataset

• FathomNet Challenge: Out-of-sample detection in the deep ocean (Kaggle competition)

• Whales from Space Dataset:  an annotated satellite image dataset of whales for training ML models

• DeepFish: a realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis

• MLAAPDE: A Machine Learning Dataset for Determining Global Earthquake Source Parameters

• AI for Understanding Earthquakes Kaggle Challenge

• airPy: Generating AI-ready data sets for air quality studies

This list of data sets has been made available as a resource to students in EEPS-DATA 1720. The course instructional team did not create and does not maintain any of these data sets, so we can not guarantee their accuracy or availability.  It is the responsibility of the student to verify the source and vet quality of any data set they choose to use in their project.

If you are familiar with other interesting data sets related to our class theme of Tackling Climate Change, please email the course staff and we'll add them to the list!