Sowing Seeds of Food Security in Africa - EosAn innovative program focused on collaboration and capacity building is looking to improve outcomes for smallholder farmers, reduce hunger, and alleviate food insecurity in sub-Saharan Africa.

Research Overview

Dr. Nakalembe's research is interdisciplinary and develops innovative methods and applications of Earth Observations and Machine Learning. Her work focuses on Africa primarily to realize the impact of research and data-driven applications in decision-making. She seeks opportunities to develop methods, systems, and approaches grounded in science but remain contextually relevant and applicable for decision-making. She implements science-driven solutions into real-world applications through collaboration and co-development with end-users. Her Ph.D. research informed the development of the remote sensing component of the Disaster Risk Financing Project, which supported over 75,000 households (370,000 people) in the region, saving the Uganda government an estimated USD 11 million in reactive food aid costs.

Harvest Africa

Research Overview

Harvest Africa

Harvest Africa Applications Framework

Harvest Africa Applications Framework

Dr. Nakalembe leads the Africa Program under NASA Harvest, which aims to develop research methods and deploy solutions for stakeholders, including government, regional, and humanitarian organizations. The Harvest Africa priorities include:

Improving monitoring and early warning systems that provide actionable data and information on agricultural productivity and food security at multiple scales  
Advancing EO-AI methods that underpin the data and systems
Transferring capacity to national and local users for decision-making and
Developing strong long-term partnerships

Publications

Op-eds

Opinion: Unlocking satellite technology for humanitarian crises

Devex. Authors: Nicki McGoh, Catherine Nakalembe // 04 October 2021

Opinion: How NASA technology helps farmers at home and abroad

AgriPulse, July 21, 2021, Authors: NASA Harvest/ University of Maryland

Sowing Seeds of Food Security in Africa

Eos Science News by AGU, Authors: C. Nakalembe, C. Justice, H. Kerner, C. Justice and I. Becker-Reshef, 25 January 2021

Journal Articles

Nakalembe, Catherine, and Hannah R. Kerner. "Considerations for AI-EO for agriculture in Sub-Saharan Africa." Environmental Research Letters (2023). Published 24 March 2023

Borges DE, Ramage S, Green D, Justice C, Nakalembe C, Whitcraft A, Barker B, Becker-Reshef I, Balagizi C, Salvi S, Ambrosia V. Earth observations into action: the systemic integration of earth observation applications into national risk reduction decision structures. Disaster Prevention and Management: An International Journal. 2023 Apr 5.

Magadzire, T., Hoell, A., Nakalembe, C., and Tongwane, M. (2022). Recent advances in agrometeorological analysis techniques for crop monitoring in support of food security early warning. Frontiers in Climate, 4:950447.

K. E. Joyce, C. L. Nakalembe, C. G ́omez, G. Suresh, K. Fickas, M. Halabisky, M. Kalamandeen, and M. A. Crowley. Discovering inclusivity in remote sensing: leaving no one behind. Frontiers in Remote Sensing, Front. Remote Sens., 01 July 2022

C. Nakalembe and H. R. Kerner. Applications and Considerations for AI-EO for Agriculture in Sub-Saharan Africa. In 36th Annu. Conf. Artif. Intell. Assoc. Adv. Artif. Intell., 2022

Nakalembe, C., Zubkova, M., Hall, J. V., Argueta, F., & Giglio, L. (2022). Impacts of large-scale refugee resettlement on LCLUC: Bidi Bidi refugee settlement, Uganda case study. Environmental Research Letters. https://doi.org/10.1088/1748-9326/ac6e48

Tseng, G., Zvonkov, I., Nakalembe, C. L., & Kerner, H. (2021). CropHarvest: A global dataset for crop-type classification. Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). Retrieved from https://openreview.net/forum?id=JtjzUXPEaCu

seng, H. Kerner, C. Nakalembe, and I. Becker-Reshef. Learning to predict crop type from heterogeneous sparse labels using meta-learning. In Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Work., pages 1111–1120, 2021

Paliyam, M., Nakalembe, C., Liu, K., Nyiawung, R., & Kerner, H. (2021). Street2Sat: A Machine Learning Pipeline for Generating Ground-truth Geo-referenced Labeled Datasets from Street-Level Images.

Adams EC, Parache HB, Cherrington E, Ellenburg WL, Mishra V, Lucey R and Nakalembe C (2021)Limitations of Remote Sensing in Assessing Vegetation Damage Due to the 2019–2021 Desert Locust Upsurge.Front. Clim. 3:714273. DOI: https://doi.org/10.3389/fclim.2021.71427

Robert Huppertz, Catherine Nakalembe, and Hannah Kerner. 2021. Using transfer learning to study burned area dynamics: A case study of Refugee settlements in West Nile, Northern Uganda. In KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, USA, 5 pages. https://doi.org/10.1145/1122445.1122456

Nakalembe, C., Becker-Reshef, I., Bonifacio, R., Hu, G., Humber, M. L., Justice, C. J., . . . Sanchez, A.(2021). A review of satellite-based global agricultural monitoring systems available for Africa. Global Food Security, 29, 100543. https://doi.org/10.1016/j.gfs.2021.100543

Shukla, S., Macharia, D., Husak, G. J., Landsfeld, M., Nakalembe, C. L., Blakeley, S. L., . . . Way-Henthorne,J. (2021). Enhancing Access and Usage of Earth Observations in Environmental Decision-Making in Eastern and Southern Africa Through Capacity Building. Frontiers in Sustainable Food Systems, 5, 504063.https://doi.org/10.3389/fsufs.2021.504063

Nakalembe, C. (2020). Urgent and critical need for sub-Saharan African countries to invest in Earth observation-based agricultural early warning and monitoring systems. Environmental Research Letters, 15(12),121002. https://doi.org/10.1088/1748-9326/abc0bb

Tseng, G., Kerner, H., Nakalembe, C., and Becker-Reshef, I. (2020). Annual and in-season mapping of cropland at field scale with sparse labels. Proceedings of the Neural Information Processing Systems (NeurIPS) Workshops, Tackling Climate Change with AI

Kerner, H., Tseng, G., Becker-Reshef, I., Nakalembe, C., Barker, B., Munshell, B., . . . Hosseini, M. (2020). Rapid Response Crop Maps in Data Sparse Regions. KDD '20 Humanitarian Mapping Workshop, 7. https://arxiv.org/abs/2006.16866

Kerner, H. R., Nakalembe, C., Becker-Reshef, I. (2020). Field-Level Crop Type Classification with K Nearest Neighbors: A Baseline for a New Kenya Smallholder Dataset. Proceedings of the 1st Computer Vision for Agriculture Workshop, International Conference on Learning Representations (ICLR2020). https://arxiv.org/abs/2004.03023

Becker-Reshef, I., Justice, C., Barker, B., Humber, M., Rembold, F., Bonifacio, R., . . .Nakalembe, c., . . .Verdin, J. (2020). Strengthening agricultural decisions in countries at risk of food insecurity: The GEOGLAMCrop Monitor for Early Warning. Remote Sensing of Environment, 237. https://doi.org/10.1016/j.rse.2019.111553

Nakalembe, C. (2018). Characterizing agricultural drought in the Karamoja sub-region of Uganda with meteorological and satellite-based indices. Natural Hazards,91(3), 837–862. https://doi.org/10.1007/s11069-017-3106-x

Laso Bayas, J. C., See, L., Perger, C., Justice, C., Nakalembe, C., Dempewolf, J., & Fritz, S. (2017). Validation of Automatically Generated Global and Regional Cropland Data Sets: The Case of Tanzania. Remote Sensing, 9(8). https://doi.org/10.3390/rs90808158.

Nakalembe, C., Dempewolf, J., & Justice, C. (2017). Agricultural land-use change in Karamoja Region, Uganda. Land Use Policy, 62, 2–12. https://doi.org/10.1016/j.landusepol.2016.11.029

Nakalembe, C. L. (2017). AGRICULTURAL LAND USE, DROUGHT IMPACTS AND VULNERABILITY: A REGIONAL CASE STUDY FOR KARAMOJA, UGANDA, Ph.D Dissertation in Geographical ScienceUniversity of Maryland. Retrieved from https://drum.lib.umd.edu/handle/1903/20320

Datasets and Tools

High resolution Cropland Extent for Karamoja Uganda 2010/11This dataset is a shapefile of Cropland extent for Karamoja derived for 2010/2011 from WorldView 1&2 panchromatic and multispectral data at 0.5 m and 1.8 m resolution respectively. The satellite images were acquired between 2010 and 2011 and obtained from The National Geospatial-Intelligence Agency (NGA) through an agreement with NASA under the NextView License (For information about the NextView License, please visit: http://cad4nasa.gsfc. nasa.gov/.). Description of the method to derive the map are included in the reference below. Nakalembe, C., Dempewolf, J., & Justice, C. (2017). Agricultural land use change in Karamoja Region , Uganda. Land Use Policy, 62, 2–12. https://doi.org/10.1016/j.landusepol.2016.11.029

CropHarvest: A global dataset for crop-type classificationCropHarvest: An ML-ready global dataset for crop-type classification

coldpress.ai | Mali (2019) Crop Type Training Datamake your AI models overachieve

Kenya Cropland Map and Non-Crop Labelled datasetThis dataset provides a 10m resolution map of cropland in Kenya for the 2019-2020 growing season (kenya_cropland_binary_2019.tif.zip) and a 10m resolution map of cropland in Busia County, Kenya for the 2020-2021 growing season (busia_cropland_binary_2020.tif.zip). Each pixel has a binary value, 0 if it does not contain crops and 1 if it does. These values were obtained by thresholding the predictions of an LSTM classifier trained on multi-spectral time series of Sentinel-2 satellite observations. A thresholding value of 0.5 was used. This dataset also provides the hand-labelled non-crop points used for training, which were created by labelling high-resolution satellite imagery in QGIS and Google Earth Pro. 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. 2020. Annual and in-season mapping of cropland at field scale with sparse labels. Tackling Climate Change with Machine Learning workshop at NeurIPS ’20: December 11th, 2020

Togo Cropland Map and Labeled DatasetThis 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.