Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling

Inland valleys (IVs) in Africa are important landscapes for rice cultivation and are targeted by national governments to attain self-sufficiency. Yet, there is limited information on the spatial distribution of IVs suitability at the national scale. In the present study, we developed an ensemble mod...

Full description

Bibliographic Details
Main Authors: Akpoti, K., Kabo-bah, A.T., Dossou-Yovo, Elliott Ronald, Groen, T.A., Zwart, Sander J.
Format: Journal Article
Language:Inglés
Published: Elsevier 2020
Subjects:
Online Access:https://hdl.handle.net/10568/107122
_version_ 1855515271859535872
author Akpoti, K.
Kabo-bah, A.T.
Dossou-Yovo, Elliott Ronald
Groen, T.A.
Zwart, Sander J.
author_browse Akpoti, K.
Dossou-Yovo, Elliott Ronald
Groen, T.A.
Kabo-bah, A.T.
Zwart, Sander J.
author_facet Akpoti, K.
Kabo-bah, A.T.
Dossou-Yovo, Elliott Ronald
Groen, T.A.
Zwart, Sander J.
author_sort Akpoti, K.
collection Repository of Agricultural Research Outputs (CGSpace)
description Inland valleys (IVs) in Africa are important landscapes for rice cultivation and are targeted by national governments to attain self-sufficiency. Yet, there is limited information on the spatial distribution of IVs suitability at the national scale. In the present study, we developed an ensemble model approach to characterize the IVs suitability for rainfed lowland rice using 4 machine learning algorithms based on environmental niche modeling (ENM) with presence-only data and background sample, namely Boosted Regression Tree (BRT), Generalized Linear Model (GLM), Maximum Entropy (MAXNT) and Random Forest (RF). We used a set of predictors that were grouped under climatic variables, agricultural water productivity and soil water content, soil chemical properties, soil physical properties, vegetation cover, and socio-economic variables. The Area Under the Curves (AUC) evaluation metrics for both training and testing were respectively 0.999 and 0.873 for BRT, 0.866 and 0.816 for GLM, 0.948 and 0.861 for MAXENT and 0.911 and 0.878 for RF. Results showed that proximity of inland valleys to roads and urban centers, elevation, soil water holding capacity, bulk density, vegetation index, gross biomass water productivity, precipitation of the wettest quarter, isothermality, annual precipitation, and total phosphorus among others were major predictors of IVs suitability for rainfed lowland rice. Suitable IVs areas were estimated at 155,000–225,000 Ha in Togo and 351,000–406,000 Ha in Benin. We estimated that 53.8% of the suitable IVs area is needed in Togo to attain self-sufficiency in rice while 60.1% of the suitable IVs area is needed in Benin to attain self-sufficiency in rice. These results demonstrated the effectiveness of an ensemble environmental niche modeling approach that combines the strengths of several models.
format Journal Article
id CGSpace107122
institution CGIAR Consortium
language Inglés
publishDate 2020
publishDateRange 2020
publishDateSort 2020
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1071222023-12-08T19:36:04Z Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling Akpoti, K. Kabo-bah, A.T. Dossou-Yovo, Elliott Ronald Groen, T.A. Zwart, Sander J. land suitability rice agricultural production environmental modelling linear models forecasting uncertainty water productivity soil water content rainfed farming climatic data soil chemicophysical properties socioeconomic environment valleys pollution environmental engineering Inland valleys (IVs) in Africa are important landscapes for rice cultivation and are targeted by national governments to attain self-sufficiency. Yet, there is limited information on the spatial distribution of IVs suitability at the national scale. In the present study, we developed an ensemble model approach to characterize the IVs suitability for rainfed lowland rice using 4 machine learning algorithms based on environmental niche modeling (ENM) with presence-only data and background sample, namely Boosted Regression Tree (BRT), Generalized Linear Model (GLM), Maximum Entropy (MAXNT) and Random Forest (RF). We used a set of predictors that were grouped under climatic variables, agricultural water productivity and soil water content, soil chemical properties, soil physical properties, vegetation cover, and socio-economic variables. The Area Under the Curves (AUC) evaluation metrics for both training and testing were respectively 0.999 and 0.873 for BRT, 0.866 and 0.816 for GLM, 0.948 and 0.861 for MAXENT and 0.911 and 0.878 for RF. Results showed that proximity of inland valleys to roads and urban centers, elevation, soil water holding capacity, bulk density, vegetation index, gross biomass water productivity, precipitation of the wettest quarter, isothermality, annual precipitation, and total phosphorus among others were major predictors of IVs suitability for rainfed lowland rice. Suitable IVs areas were estimated at 155,000–225,000 Ha in Togo and 351,000–406,000 Ha in Benin. We estimated that 53.8% of the suitable IVs area is needed in Togo to attain self-sufficiency in rice while 60.1% of the suitable IVs area is needed in Benin to attain self-sufficiency in rice. These results demonstrated the effectiveness of an ensemble environmental niche modeling approach that combines the strengths of several models. 2020-03 2020-02-18T06:47:39Z 2020-02-18T06:47:39Z Journal Article https://hdl.handle.net/10568/107122 en Limited Access Elsevier Akpoti, K.; Kabo-bah, A. T.; Dossou-Yovo, E. R.; Groen, T. A.; Zwart, Sander J. 2020. Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling. Science of the Total Environment, 19p. (Online first) doi: 10.1016/j.scitotenv.2019.136165
spellingShingle land suitability
rice
agricultural production
environmental modelling
linear models
forecasting
uncertainty
water productivity
soil water content
rainfed farming
climatic data
soil chemicophysical properties
socioeconomic environment
valleys
pollution
environmental engineering
Akpoti, K.
Kabo-bah, A.T.
Dossou-Yovo, Elliott Ronald
Groen, T.A.
Zwart, Sander J.
Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling
title Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling
title_full Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling
title_fullStr Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling
title_full_unstemmed Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling
title_short Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling
title_sort mapping suitability for rice production in inland valley landscapes in benin and togo using environmental niche modeling
topic land suitability
rice
agricultural production
environmental modelling
linear models
forecasting
uncertainty
water productivity
soil water content
rainfed farming
climatic data
soil chemicophysical properties
socioeconomic environment
valleys
pollution
environmental engineering
url https://hdl.handle.net/10568/107122
work_keys_str_mv AT akpotik mappingsuitabilityforriceproductionininlandvalleylandscapesinbeninandtogousingenvironmentalnichemodeling
AT kabobahat mappingsuitabilityforriceproductionininlandvalleylandscapesinbeninandtogousingenvironmentalnichemodeling
AT dossouyovoelliottronald mappingsuitabilityforriceproductionininlandvalleylandscapesinbeninandtogousingenvironmentalnichemodeling
AT groenta mappingsuitabilityforriceproductionininlandvalleylandscapesinbeninandtogousingenvironmentalnichemodeling
AT zwartsanderj mappingsuitabilityforriceproductionininlandvalleylandscapesinbeninandtogousingenvironmentalnichemodeling