Data-driven similar response units for agricultural technology targeting: An example from Ethiopia

Ethiopia has heterogeneous topographic, climatic and socio-ecological systems. Recommendations of agricultural inputs and management practices based on coarse domains such as agro-ecological zones (AEZ) may not lead to accurate targeting, mainly due to large intra-zone variations. The lack of well-t...

Full description

Bibliographic Details
Main Authors: Tamene, Lulseged D., Abera, Wuletawu, Bendito, Eduardo, Erkossa, Teklu, Tariku, Meklit, Sewnet, Habtamu, Tibebe, Degefie, Sied, Jema, Feyisa, Gudina, Wondie, Menale, Tesfaye, Kindie
Format: Journal Article
Language:Inglés
Published: Cambridge University Press 2022
Subjects:
Online Access:https://hdl.handle.net/10568/120934
_version_ 1855535676097822720
author Tamene, Lulseged D.
Abera, Wuletawu
Bendito, Eduardo
Erkossa, Teklu
Tariku, Meklit
Sewnet, Habtamu
Tibebe, Degefie
Sied, Jema
Feyisa, Gudina
Wondie, Menale
Tesfaye, Kindie
author_browse Abera, Wuletawu
Bendito, Eduardo
Erkossa, Teklu
Feyisa, Gudina
Sewnet, Habtamu
Sied, Jema
Tamene, Lulseged D.
Tariku, Meklit
Tesfaye, Kindie
Tibebe, Degefie
Wondie, Menale
author_facet Tamene, Lulseged D.
Abera, Wuletawu
Bendito, Eduardo
Erkossa, Teklu
Tariku, Meklit
Sewnet, Habtamu
Tibebe, Degefie
Sied, Jema
Feyisa, Gudina
Wondie, Menale
Tesfaye, Kindie
author_sort Tamene, Lulseged D.
collection Repository of Agricultural Research Outputs (CGSpace)
description Ethiopia has heterogeneous topographic, climatic and socio-ecological systems. Recommendations of agricultural inputs and management practices based on coarse domains such as agro-ecological zones (AEZ) may not lead to accurate targeting, mainly due to large intra-zone variations. The lack of well-targeted recommendations may contribute to the underperformance of promising technologies. Therefore, there is a need to define units where similar environmental and biophysical features prevail, based on which specific recommendations can be made for similar response units (SRUs). We used unsupervised machine learning algorithms to identify areas of high similarity or homogeneous zones called ‘SRUs’ that can guide the targeting of agricultural technologies. SRUs are landscape entities defined by integrating relevant environmental covariates with the intention to identify areas of similar responses. Using environmental spatial data layers such as edaphic and ecological variables for delineation of the SRUs, we applied K- and X-means clustering techniques to generate various granular levels of zonation and define areas of high similarity. The results of the clustering were validated through expert consultation and by comparison with an existing operational AEZ map of Ethiopia. We also augmented validation of the heterogeneity of the SRUs by using field-based crop response to fertiliser application experimental data. The expert consultation highlighted that the SRUs can provide improved clustering of areas of high similarity for targeting interventions. Comparison with the AEZ map indicated that SRUs with the same number of AEZ units captured heterogeneity better with less within-cluster variability of the former. In addition, SRUs show lower within-cluster variability to optimal crop response to fertiliser application compared with AEZs with the same number of classes. This implies that the SRUs can be used for refined agricultural input and technology targeting. The work in this study also developed an operational framework that users can deploy to fetch data from the cloud and generate SRUs for their areas of interest.
format Journal Article
id CGSpace120934
institution CGIAR Consortium
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Cambridge University Press
publisherStr Cambridge University Press
record_format dspace
spelling CGSpace1209342025-11-12T06:51:16Z Data-driven similar response units for agricultural technology targeting: An example from Ethiopia Tamene, Lulseged D. Abera, Wuletawu Bendito, Eduardo Erkossa, Teklu Tariku, Meklit Sewnet, Habtamu Tibebe, Degefie Sied, Jema Feyisa, Gudina Wondie, Menale Tesfaye, Kindie appropriate technology machine learning policies agriculture farming systems tecnología apropiada aprendizaje electrónico políticas technology transfer fertilizer applications ethiopia agroecology Ethiopia has heterogeneous topographic, climatic and socio-ecological systems. Recommendations of agricultural inputs and management practices based on coarse domains such as agro-ecological zones (AEZ) may not lead to accurate targeting, mainly due to large intra-zone variations. The lack of well-targeted recommendations may contribute to the underperformance of promising technologies. Therefore, there is a need to define units where similar environmental and biophysical features prevail, based on which specific recommendations can be made for similar response units (SRUs). We used unsupervised machine learning algorithms to identify areas of high similarity or homogeneous zones called ‘SRUs’ that can guide the targeting of agricultural technologies. SRUs are landscape entities defined by integrating relevant environmental covariates with the intention to identify areas of similar responses. Using environmental spatial data layers such as edaphic and ecological variables for delineation of the SRUs, we applied K- and X-means clustering techniques to generate various granular levels of zonation and define areas of high similarity. The results of the clustering were validated through expert consultation and by comparison with an existing operational AEZ map of Ethiopia. We also augmented validation of the heterogeneity of the SRUs by using field-based crop response to fertiliser application experimental data. The expert consultation highlighted that the SRUs can provide improved clustering of areas of high similarity for targeting interventions. Comparison with the AEZ map indicated that SRUs with the same number of AEZ units captured heterogeneity better with less within-cluster variability of the former. In addition, SRUs show lower within-cluster variability to optimal crop response to fertiliser application compared with AEZs with the same number of classes. This implies that the SRUs can be used for refined agricultural input and technology targeting. The work in this study also developed an operational framework that users can deploy to fetch data from the cloud and generate SRUs for their areas of interest. 2022 2022-08-24T13:43:38Z 2022-08-24T13:43:38Z Journal Article https://hdl.handle.net/10568/120934 en Open Access application/pdf Cambridge University Press Tamene, L., Abera, W., Bendito, E., Erkossa, T., Tariku, M., Sewnet, H., Tibebe, D., Sied, J., Feyisa, G., Wondie, M., & Tesfaye, K. (2022). Data-driven similar response units for agricultural technology targeting: An example from Ethiopia. Experimental Agriculture, 58. https://doi.org/10.1017/s0014479722000126
spellingShingle appropriate technology
machine learning
policies
agriculture
farming systems
tecnología apropiada
aprendizaje electrónico
políticas
technology transfer
fertilizer applications
ethiopia
agroecology
Tamene, Lulseged D.
Abera, Wuletawu
Bendito, Eduardo
Erkossa, Teklu
Tariku, Meklit
Sewnet, Habtamu
Tibebe, Degefie
Sied, Jema
Feyisa, Gudina
Wondie, Menale
Tesfaye, Kindie
Data-driven similar response units for agricultural technology targeting: An example from Ethiopia
title Data-driven similar response units for agricultural technology targeting: An example from Ethiopia
title_full Data-driven similar response units for agricultural technology targeting: An example from Ethiopia
title_fullStr Data-driven similar response units for agricultural technology targeting: An example from Ethiopia
title_full_unstemmed Data-driven similar response units for agricultural technology targeting: An example from Ethiopia
title_short Data-driven similar response units for agricultural technology targeting: An example from Ethiopia
title_sort data driven similar response units for agricultural technology targeting an example from ethiopia
topic appropriate technology
machine learning
policies
agriculture
farming systems
tecnología apropiada
aprendizaje electrónico
políticas
technology transfer
fertilizer applications
ethiopia
agroecology
url https://hdl.handle.net/10568/120934
work_keys_str_mv AT tamenelulsegedd datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT aberawuletawu datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT benditoeduardo datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT erkossateklu datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT tarikumeklit datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT sewnethabtamu datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT tibebedegefie datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT siedjema datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT feyisagudina datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT wondiemenale datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia
AT tesfayekindie datadrivensimilarresponseunitsforagriculturaltechnologytargetinganexamplefromethiopia