Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach

In this study, we aimed to map the frequency of recurrent desert locust invasions to predict future invasions and understand their correlation with climatic variables. Utilizing global locust data from the Desert Locust Hub (FAO) covering 1985 to 2020, we formulated an optimization problem to minimi...

Full description

Bibliographic Details
Main Authors: Agboka, K.M., Abdel-Rahman, E.M., Kimathi, E., Sokame, B.M., Landman, T., Niassy, S., Tonnang, H.E.Z.
Format: Journal Article
Language:Inglés
Published: 2025
Subjects:
Online Access:https://hdl.handle.net/10568/180628
_version_ 1855530992282894336
author Agboka, K.M.
Abdel-Rahman, E.M.
Kimathi, E.
Sokame, B.M.
Landman, T.
Niassy, S.
Tonnang, H.E.Z.
author_browse Abdel-Rahman, E.M.
Agboka, K.M.
Kimathi, E.
Landman, T.
Niassy, S.
Sokame, B.M.
Tonnang, H.E.Z.
author_facet Agboka, K.M.
Abdel-Rahman, E.M.
Kimathi, E.
Sokame, B.M.
Landman, T.
Niassy, S.
Tonnang, H.E.Z.
author_sort Agboka, K.M.
collection Repository of Agricultural Research Outputs (CGSpace)
description In this study, we aimed to map the frequency of recurrent desert locust invasions to predict future invasions and understand their correlation with climatic variables. Utilizing global locust data from the Desert Locust Hub (FAO) covering 1985 to 2020, we formulated an optimization problem to minimize grid size, ensuring each cell contained data for at least 35 years to calculate the invasion frequency using the ratio of locust presence per year. The computational implementation used Python, for numerical computations and geographical data handling. The model incorporated climatic predictors from the NASA POWER project, including relative humidity, temperature, evapotranspiration, wind speed, and precipitation. Using an Adaptive Neuro-Fuzzy Inference System (ANFIS) combined with a genetic algorithm (GA), we refined our predictive capabilities. The model underwent 3000 iterations, with an optimized crossover and mutation rate enhancing the genetic algorithm’s performance. The model demonstrated strong predictability and transferability with an R2of 0.87, an root mean square error (RMSE) of 0.44, and a low Mean Absolute Error (MAE) of 0.30 to 0.40. The model predicted that 40% of the study area is frequently invaded by desert locusts, highlighting the African Sahel, Arabian Peninsula, and parts of the Maghreb and Middle East as high-risk regions. These findings provide a robust framework for predicting desert locust invasions and developing effective management strategies.
format Journal Article
id CGSpace180628
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
record_format dspace
spelling CGSpace1806282026-01-26T10:04:43Z Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach Agboka, K.M. Abdel-Rahman, E.M. Kimathi, E. Sokame, B.M. Landman, T. Niassy, S. Tonnang, H.E.Z. insect pests optimization methods climate change food security In this study, we aimed to map the frequency of recurrent desert locust invasions to predict future invasions and understand their correlation with climatic variables. Utilizing global locust data from the Desert Locust Hub (FAO) covering 1985 to 2020, we formulated an optimization problem to minimize grid size, ensuring each cell contained data for at least 35 years to calculate the invasion frequency using the ratio of locust presence per year. The computational implementation used Python, for numerical computations and geographical data handling. The model incorporated climatic predictors from the NASA POWER project, including relative humidity, temperature, evapotranspiration, wind speed, and precipitation. Using an Adaptive Neuro-Fuzzy Inference System (ANFIS) combined with a genetic algorithm (GA), we refined our predictive capabilities. The model underwent 3000 iterations, with an optimized crossover and mutation rate enhancing the genetic algorithm’s performance. The model demonstrated strong predictability and transferability with an R2of 0.87, an root mean square error (RMSE) of 0.44, and a low Mean Absolute Error (MAE) of 0.30 to 0.40. The model predicted that 40% of the study area is frequently invaded by desert locusts, highlighting the African Sahel, Arabian Peninsula, and parts of the Maghreb and Middle East as high-risk regions. These findings provide a robust framework for predicting desert locust invasions and developing effective management strategies. 2025 2026-01-26T10:04:42Z 2026-01-26T10:04:42Z Journal Article https://hdl.handle.net/10568/180628 en Limited Access Agboka, K.M., Abdel-Rahman, E.M., Kimathi, E., Sokame, B.M., Landman, T., Niassy, S. & Tonnang, H.E.Z. (2025). Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach. International Journal of Tropical Insect Science, 1-10.
spellingShingle insect pests
optimization methods
climate change
food security
Agboka, K.M.
Abdel-Rahman, E.M.
Kimathi, E.
Sokame, B.M.
Landman, T.
Niassy, S.
Tonnang, H.E.Z.
Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach
title Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach
title_full Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach
title_fullStr Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach
title_full_unstemmed Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach
title_short Prediction of recurrent desert locust invasions under climate variability in the extended Sahara Desert: an evolutionary adaptive Neuro-Fuzzy approach
title_sort prediction of recurrent desert locust invasions under climate variability in the extended sahara desert an evolutionary adaptive neuro fuzzy approach
topic insect pests
optimization methods
climate change
food security
url https://hdl.handle.net/10568/180628
work_keys_str_mv AT agbokakm predictionofrecurrentdesertlocustinvasionsunderclimatevariabilityintheextendedsaharadesertanevolutionaryadaptiveneurofuzzyapproach
AT abdelrahmanem predictionofrecurrentdesertlocustinvasionsunderclimatevariabilityintheextendedsaharadesertanevolutionaryadaptiveneurofuzzyapproach
AT kimathie predictionofrecurrentdesertlocustinvasionsunderclimatevariabilityintheextendedsaharadesertanevolutionaryadaptiveneurofuzzyapproach
AT sokamebm predictionofrecurrentdesertlocustinvasionsunderclimatevariabilityintheextendedsaharadesertanevolutionaryadaptiveneurofuzzyapproach
AT landmant predictionofrecurrentdesertlocustinvasionsunderclimatevariabilityintheextendedsaharadesertanevolutionaryadaptiveneurofuzzyapproach
AT niassys predictionofrecurrentdesertlocustinvasionsunderclimatevariabilityintheextendedsaharadesertanevolutionaryadaptiveneurofuzzyapproach
AT tonnanghez predictionofrecurrentdesertlocustinvasionsunderclimatevariabilityintheextendedsaharadesertanevolutionaryadaptiveneurofuzzyapproach