119 research outputs found
Hand Labelled Crop / Non Crop datasets
No full textThis dataset provides the hand-labelled crop / non-crop points used for training, which were created by labelling high-resolution satellite imagery in QGIS and Google Earth Pro. Data is available for Ethiopia, Sudan, Togo and Kenya.
Code used to process these points is available in the following github repository: https://github.com/nasaharvest/crop-maml
For more information, or if you use any part of this dataset, please refer to / cite the following paper: Gabriel Tseng, Hannah Kerner, Catherine Nakalembe and Inbal Becker-Reshef. 2021. Learning to predict crop type from heterogeneous sparse labels using meta-learning. GeoVision Workshop at CVPR ’21: June 19th, 202
Crop Conditions and Prospects Through Satellite Earth Observations
No full textInbal Becker-Rashef POLICY SEMINAR Global commodity prices and food security: Navigating new challenges and learning from the past MAR 9, 2022 - 9:30 TO 11:30AM ES
Togo Cropland Map and Labeled Dataset
No full textThis dataset provides a 10 m resolution map of cropland in Togo (togo_cropland_2019.zip). Each pixel represents a posterior probability (ranging 0 to 1) that the pixel contains crops, predicted using an LSTM classifier and multi-spectral time series of Sentinel-2 satellite observations. For more details on the method, please see Kerner and Tseng, et al. (full reference below).
This dataset also provides the hand-labeled polygons used for training (crop_merged_v2.zi, noncrop_merged_v2.zip) and testing (togo_test_majority.zip) the model, which were created by experts based on photointerpretation of high-resolution imagery (primarily SkySat and PlanetScope) in QGIS and Google Earth Pro.
If you use any part of this dataset, please cite the following paper: Hannah Kerner, Gabriel Tseng, Inbal Becker-Reshef, Catherine Nakalembe, Brian Barker, Blake Munshell, Madhava Paliyam, and Mehdi Hosseini. 2020. Rapid Response Crop Maps in Data Sparse Regions. In review for KDD ’20: ACMSIGKDD Conference on Knowledge Discovery and Data Mining Workshops, August 22–27, 2020, San Diego, CA
Satellite Data for Corn and Soybean Fields + Other Land Cover: Illinois, US, 2017-2019
No full textThese are the datasets associated with the paper:
Hannah Kerner, Ritvik Sahajpal, Sergii Skakun, Inbal Becker-Reshef, Brian Barker, Mehdi Hosseini, Estefania Puricelli, and Patrick Gray. 2020. Resilient In-Season Crop Type Classification in Multispectral Satellite Observations using Growth Stage Normalization. In KDD ’20: ACM Special Interest Group (SIG) on Knowledge Discovery and Data Mining Conference Workshops, August 23–27, 2020, San Diego, CA.
The code that uses these datasets can be found at: https://github.com/nasaharvest/croptype-mapping-gs
Comparison of Cropland Maps Derived from Land Cover Maps in Sub-Saharan Africa
No full textThis data repository provides the datasets associated with analysis conducted in Kerner et al. (2023), citation below.
The CSV file `intercomparison-results.csv` gives a table metrics for each of 11 land cover maps (plus a majority vote ensemble of all maps) evaluated using the reference dataset for each of 8 countries (Kenya, Rwanda, Uganda, Tanzania, Mali, Malawi, Togo, and Zambia). The reference datasets are provided as zip files. To ensure these datasets can be used for independent evaluation and comparison between maps in the future, the reference datasets should ONLY be used for final, independent evaluation of data products/model outputs; they should NOT be used for training models, tuning hyperparameters, or any other decisions during model/map development.
The provided tif files contain the consensus maps (sum of all 11 maps) used to compute consensus statistics in Kerner et al. (2023).
Kerner, H., Nakalembe, C., Yang, A., Zvonkov, I., McWeeny, R., Tseng, G., and Becker-Reshef, I. (2023). How accurate are existing land cover maps for agriculture in Sub-Saharan Africa? Under review
A GENERALIZED APPROACH TO WHEAT YIELD FORECASTING USING EARTH OBSERVATIONS: DATA CONSIDERATIONS, APPLICATION, AND RELEVANCE.
Get PDFIn recent years there has been a dramatic increase in the demand for timely, comprehensive global agricultural intelligence. The issue of food security has rapidly risen to the top of government agendas around the world as the recent lack of food access led to unprecedented food prices, hunger, poverty, and civil conflict. Timely information on global crop production is indispensable for combating the growing stress on the world's crop production, for stabilizing food prices, developing effective agricultural policies, and for coordinating responses to regional food shortages.
Earth Observations (EO) data offer a practical means for generating such information as they provide global, timely, cost-effective, and synoptic information on crop condition and distribution. Their utility for crop production forecasting has long been recognized and demonstrated across a wide range of scales and geographic regions. Nevertheless it is widely acknowledged that EO data could be better utilized within the operational monitoring systems and thus there is a critical need for research focused on developing practical robust methods for agricultural monitoring. Within this context this dissertation focused on advancing EO-based methods for crop yield forecasting and on demonstrating the potential relevance for adopting EO-based crop forecasts for providing timely reliable agricultural intelligence. This thesis made contributions to this field by developing and testing a robust EO-based method for wheat production forecasting at state to national scales using available and easily accessible data. The model was developed in Kansas (KS) using coarse resolution normalized difference vegetation index (NDVI) time series data in conjunction with out-of-season wheat masks and was directly applied in Ukraine to assess its transferability. The model estimated yields within 7% in KS and 10% in Ukraine of final estimates 6 weeks prior to harvest. The relevance of adopting such methods to provide timely reliable information to crop commodity markets is demonstrated through a 2010 case study
GEOGLAM (GEO Global Agricultural Monitoring) Crop Assessment Tool
No full textThe Group on Earth Observations, a partnership of governments and international organizations, developed the Global Agricultural Monitoring (GEOGLAM) initiative in response to the growing calls for improved agricultural information. The goal of GEOGLAM is to strengthen the international community’s capacity to produce and disseminate relevant, timely and accurate forecasts of agricultural production at national, regional and global scales through the use of Earth Observations (EO), which include satellite and ground-based observations. This initiative is designed to build on existing agricultural monitoring programs and initiatives at national, regional and global levels and to enhance and strengthen them through international networking, operationally focused research, and data/method sharing.
The GEOGLAM Crop Monitor provides the Agricultural Market Information System (AMIS) with an international and transparent multi-source, consensus assessment of crop growing conditions, status, and agro-climatic conditions, likely to impact global production. This activity covers the four primary crop types (wheat, maize, rice, and soy) within the main agricultural producing regions of the AMIS countries. These assessments have been produced operationally since September 2013 and are published in the AMIS Market Monitor Bulletin. The Crop Monitor reports provide cartographic and textual summaries of crop conditions as of the 28th of each month, according to crop type.
Sources and Disclaimers: The Crop Monitor assessment is conducted by GEOGLAM with coordination from the University of Maryland. Inputs are from the following partners (in alphabetical order): Argentina (Buenos Aires Grains Exchange, INTA), Asia Rice Countries (AFSIS, ASEAN+3 & Asia RiCE), Australia (ABARES & CSIRO), Brazil (CONAB & INPE), Canada (AAFC), China (CAS), EU (EC JRC MARS), Indonesia (LAPAN & MOA), International (CIMMYT, FAO, IFPRI & IRRI), Japan (JAXA ), Mexico (SIAP), Russian Federation (IKI), South Africa (ARC & GeoTerraImage & SANSA), Thailand (GISTDA & OAE), Ukraine (NASU-NSAU & UHMC), USA (NASA, UMD, USGS – FEWS NET, USDA (FAS, NASS)), Viet nam (VAST & VIMHE-MARD). The findings and conclusions in this joint multi-agency report are consensual statements from the GEOGLAM experts, and do not necessarily reflect those of the individual agencies represented by these experts. Map data sources: Major crop type areas based on the IFPRI/IIASA SPAM 2005 beta release (2013), USDA/NASS 2013 CDL, 2013 AAFC Annual Crop Inventory Map, GLAM/UMD, GLAD/UMD, Australian Land Use and Management Classification (Version 7), SIAP, ARC, and JRC. The GEOGLAM crop calendars are compiled with information from AAFC, ABARES, ARC, Asia RiCE, Bolsa de cereales, CONAB, INPE, JRC, FAO, FEWS NET, IKI, INTA, SIAP, UHMC, USDA FAS, and USDA NASS. Resources in this dataset:Resource Title: GEOGLAM Crop Assessment Tool (web site) . File Name: Web Page, url: https://earthobservations.org/geoglam.php GEOGLAM contains a web-based dashboard to manipulate data, including satellite data, integrating them with ground-based and other in situ measurements. "The initiative will contribute to generating reliable, accurate, timely and sustained crop monitoring information and yield forecasts."
GEOGLAM Crop Assessment Tool Requirements:
•Users must be registered in order to use the commenting features
•A modern browser is recommended (IE10+, Firefox22+, Chrome27+)
•Popup blockers should be disabled if using the table-based Crop Impact Assessment feature
•Data is provided by Crop Monitor Group partners
Crop Monitor tool can be found at https://cropmonitor.org/index.php/eodatatools/cmet/</p
Evaluating the impacts of drought on crop production from satellite observations: A case study in Kansas
No full textEvaluation of the ASCAT surface soil moisture product for agricultural drought monitoring in USA
No full text- …
