A Mixed Model Approach to Vegetation Condition Prediction Using Artificial Neural Networks (ANN): Case of Kenya’s Operational Drought Monitoring

Abstract

Droughts, with their increasing frequency of occurrence, continue to negatively affect livelihoods and elements at risk. For example, the 2011 in drought in east Africa has caused massive losses document to have cost the Kenyan economy over $12bn. With the foregoing, the demand for ex-ante drought monitoring systems is ever-increasing. The study uses 10 precipitation and vegetation variables that are lagged over 1, 2 and 3-month time-steps to predict drought situations. In the model space search for the most predictive artificial neural network (ANN) model, as opposed to the traditional greedy search for the most predictive variables, we use the General Additive Model (GAM) approach. Together with a set of assumptions, we thereby reduce the cardinality of the space of models. Even though we build a total of 102 GAM models, only 21 have R 2 greater than 0.7 and are thus subjected to the ANN process. The ANN process itself uses the brute-force approach that automatically partitions the training data into 10 sub-samples, builds the ANN models in these samples and evaluates their performance using multiple metrics. The results show the superiority of 1-month lag of the variables as compared to longer time lags of 2 and 3 months. The champion ANN model recorded an R 2 of 0.78 in model testing using the out-of-sample data. This illustrates its ability to be a good predictor of drought situations 1-month ahead. Investigated as a classifier, the champion has a modest accuracy of 66% and a multi-class area under the ROC curve (AUROC) of 89.99%

Model Ensembles of Artificial Neural Networks and Support Vector Regression for Improved Accuracy in the Prediction of Vegetation Conditions and Droughts in Four Northern Kenya Counties

“…The key assumption made by the study is that for clarity and interpretability of models, one variable of same category is sufficient in a single model. This assumption was validated for soundness in Adede et al (2019). The process of model space reduction is presented in Figure 4.…”

“…The study area ( Figure 1) is also documented in Adede et al (2019) as covering an area of over 215000km 2 and is located in Northern Kenya and covers four counties that are classified as arid counties within Kenya's arid and semi-arid lands (ASALs). The area is characterized by both low rainfall and low vegetation cover with an average normalized difference vegetation index (NDVI) of below 0.4 except for May and Nov that peaks at 0.43.…”

“…Increasingly, the use of multiple variables in predictive drought system is gaining currency in an approach where multiple indices are used in to build the predictive systems. Such systems include the us of 11 variables and indices in Tadesse et al (2014) and that in Adede et al (2019) that uses 10 variables in the prediciton of future vegetation conditions.…”

Bibliometric Analysis of Methods and Tools for Drought Monitoring and Prediction in Africa

“…The indigo colour cluster has the work by [88] in 2014 as the first publication and cited by [89][90][91]. The research aimed at developing an experimental drought monitoring tool that predicts the vegetation condition (vegetation outlook).…”

“…Studies in this cluster are centred on agricultural drought prediction. Their methods include regression-tree technique [88], classification and regression tree (CART) modelling technique [89], ML, and general additive model (GAM) technique [90], and Vegout-UBN model [91]. Among their findings is the ex-ante drought early warning systems capable of offering drought forecasts with enough lead times.…”