African Media Law (Media/Law) | 24 December 2000
Machine Learning Models for Climate Prediction and Adaptation in Guinea
S, a, n, d, y, b, a, T, r, a, o, r, e, ,, S, a, l, l, o, u, B, a, u, m, i, ,, D, a, k, o, u, r, S, y, l, l, a, ,, K, a, m, a, r, a, D, i, o, p
Abstract
Climate change poses significant challenges to Guinea's agricultural productivity and socio-economic development. Machine learning algorithms were employed on historical weather data from the National Meteorological Agency of Guinea, including temperature and precipitation patterns over a decade (-). The machine learning models achieved an R-squared value of 0.78 for predicting temperature variations and 0.65 for rainfall predictions. The models demonstrated high predictive power, with potential to inform climate-resilient agricultural practices in Guinea. Implement the recommended climate adaptation strategies based on the machine learning-predicted climate scenarios. Model estimation used $\hat{\theta}=argmin<em>{\theta}\sum</em>i\ell(y<em>i,f</em>\theta(x<em>i))+\lambda\lVert\theta\rVert</em>2^2$, with performance evaluated using out-of-sample error.