Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda

East African highland banana (Musa acuminata genome group AAA-EA; hereafter referred to as banana) is critical for Uganda’s food supply, hence our aim to map current distribution and to understand changes in banana production areas over the past five decades. We collected banana presence/absence dat...

Full description

Bibliographic Details
Main Authors: Ochola, D., Boekelo, B., Ven, G.W. van de, Taulya, G., Kubiriba, Jerome, Asten, Piet J.A. van, Giller, Kenneth E.
Format: Journal Article
Language:Inglés
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10568/126738
_version_ 1855536670597709824
author Ochola, D.
Boekelo, B.
Ven, G.W. van de
Taulya, G.
Kubiriba, Jerome
Asten, Piet J.A. van
Giller, Kenneth E.
author_browse Asten, Piet J.A. van
Boekelo, B.
Giller, Kenneth E.
Kubiriba, Jerome
Ochola, D.
Taulya, G.
Ven, G.W. van de
author_facet Ochola, D.
Boekelo, B.
Ven, G.W. van de
Taulya, G.
Kubiriba, Jerome
Asten, Piet J.A. van
Giller, Kenneth E.
author_sort Ochola, D.
collection Repository of Agricultural Research Outputs (CGSpace)
description East African highland banana (Musa acuminata genome group AAA-EA; hereafter referred to as banana) is critical for Uganda’s food supply, hence our aim to map current distribution and to understand changes in banana production areas over the past five decades. We collected banana presence/absence data through an online survey based on high-resolution satellite images and coupled this data with independent covariates as inputs for ensemble machine learning prediction of current banana distribution. We assessed geographic shifts of production areas using spatially explicit differences between the 1958 and 2016 banana distribution maps. The biophysical factors associated with banana spatial distribution and geographic shift were determined using a logistic regression model and classification and regression tree, respectively. Ensemble models were superior (AUC = 0.895; 0.907) compared to their constituent algorithms trained with 12 and 17 covariates, respectively: random forests (AUC = 0.883; 0.901), gradient boosting machines (AUC = 0.878; 0.903), and neural networks (AUC = 0.870; 0.890). The logistic regression model (AUC = 0.879) performance was similar to that for the ensemble model and its constituent algorithms. In 2016, banana cultivation was concentrated in the western (44%) and central (36%) regions, while only a small proportion was in the eastern (18%) and northern (2%) regions. About 60% of increased cultivation since 1958 was in the western region; 50% of decreased cultivation in the eastern region; and 44% of continued cultivation in the central region. Soil organic carbon, soil pH, annual precipitation, slope gradient, bulk density and blue reflectance were associated with increased banana cultivation while precipitation seasonality and mean annual temperature were associated with decreased banana cultivation over the past 50 years. The maps of spatial distribution and geographic shift of banana can support targeting of context-specific intensification options and policy advocacy to avert agriculture driven environmental degradation.
format Journal Article
id CGSpace126738
institution CGIAR Consortium
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
record_format dspace
spelling CGSpace1267382025-11-11T10:43:09Z Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda Ochola, D. Boekelo, B. Ven, G.W. van de Taulya, G. Kubiriba, Jerome Asten, Piet J.A. van Giller, Kenneth E. bananas fruit crops geography machine learning geographical distribution crops uganda East African highland banana (Musa acuminata genome group AAA-EA; hereafter referred to as banana) is critical for Uganda’s food supply, hence our aim to map current distribution and to understand changes in banana production areas over the past five decades. We collected banana presence/absence data through an online survey based on high-resolution satellite images and coupled this data with independent covariates as inputs for ensemble machine learning prediction of current banana distribution. We assessed geographic shifts of production areas using spatially explicit differences between the 1958 and 2016 banana distribution maps. The biophysical factors associated with banana spatial distribution and geographic shift were determined using a logistic regression model and classification and regression tree, respectively. Ensemble models were superior (AUC = 0.895; 0.907) compared to their constituent algorithms trained with 12 and 17 covariates, respectively: random forests (AUC = 0.883; 0.901), gradient boosting machines (AUC = 0.878; 0.903), and neural networks (AUC = 0.870; 0.890). The logistic regression model (AUC = 0.879) performance was similar to that for the ensemble model and its constituent algorithms. In 2016, banana cultivation was concentrated in the western (44%) and central (36%) regions, while only a small proportion was in the eastern (18%) and northern (2%) regions. About 60% of increased cultivation since 1958 was in the western region; 50% of decreased cultivation in the eastern region; and 44% of continued cultivation in the central region. Soil organic carbon, soil pH, annual precipitation, slope gradient, bulk density and blue reflectance were associated with increased banana cultivation while precipitation seasonality and mean annual temperature were associated with decreased banana cultivation over the past 50 years. The maps of spatial distribution and geographic shift of banana can support targeting of context-specific intensification options and policy advocacy to avert agriculture driven environmental degradation. 2022-02-17 2023-01-10T10:52:53Z 2023-01-10T10:52:53Z Journal Article https://hdl.handle.net/10568/126738 en Open Access application/pdf Ochola, D., Boekelo, B., van de Ven, G.W., Taulya, G., Kubiriba, J., van Asten, P. & Giller, K. (2022). Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda. PloS ONE, 17(2): 0263439, 1-28.
spellingShingle bananas
fruit crops
geography
machine learning
geographical distribution
crops
uganda
Ochola, D.
Boekelo, B.
Ven, G.W. van de
Taulya, G.
Kubiriba, Jerome
Asten, Piet J.A. van
Giller, Kenneth E.
Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda
title Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda
title_full Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda
title_fullStr Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda
title_full_unstemmed Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda
title_short Mapping spatial distribution and geographic shifts of east African highland banana (Musa spp.) in Uganda
title_sort mapping spatial distribution and geographic shifts of east african highland banana musa spp in uganda
topic bananas
fruit crops
geography
machine learning
geographical distribution
crops
uganda
url https://hdl.handle.net/10568/126738
work_keys_str_mv AT ocholad mappingspatialdistributionandgeographicshiftsofeastafricanhighlandbananamusasppinuganda
AT boekelob mappingspatialdistributionandgeographicshiftsofeastafricanhighlandbananamusasppinuganda
AT vengwvande mappingspatialdistributionandgeographicshiftsofeastafricanhighlandbananamusasppinuganda
AT taulyag mappingspatialdistributionandgeographicshiftsofeastafricanhighlandbananamusasppinuganda
AT kubiribajerome mappingspatialdistributionandgeographicshiftsofeastafricanhighlandbananamusasppinuganda
AT astenpietjavan mappingspatialdistributionandgeographicshiftsofeastafricanhighlandbananamusasppinuganda
AT gillerkennethe mappingspatialdistributionandgeographicshiftsofeastafricanhighlandbananamusasppinuganda