Integration of Machine Learning and AI With Geospatial Analysis

View Sample PDF

Author(s): Oladapo Muyiwa Oladoja (Abiola Ajimobi Technical University, Ibadan, Nigeria), Latifat Adebisi Abimbola (Abiola Ajimobi Technical University, Ibadan, Nigeria)and Elizabeth Ayodele Oladejo (Abiola Ajimobi Technical University, Ibadan, Nigeria)
Copyright: 2026
Pages: 28
Source title: Advancing Environmental Research Through Applied GIS and Remote Sensing
Source Author(s)/Editor(s): Jamal Al Karkouri (Ibn Tofail University, Morocco), Adil Moumane (Ibn Tofail University, Morocco), Abdessamad Elmotawakkil (Ibn Tofail University, Morocco)and Mouhcine Batchi (Ibn Tofail University, Morocco)
DOI: 10.4018/979-8-3373-6608-1.ch008

Keywords: Engineering Science Reference / Environment & Agriculture / Environmental Science / Geographic Information Systems

Purchase

View Integration of Machine Learning and AI With Geospatial Analysis on the publisher's website for pricing and purchasing information.

Abstract

The aim of the chapter is to provide a more comprehensive vision of how machine learning (ML) and artificial intelligence (AI) technologies can be used together with geospatial analysis to help solve modern environmental problems. This study shows that spatial data, remote sensing, and powerful computational techniques can be used to transform environmental monitoring, prediction, and decision-making processes using the power of ML/AI-enhanced geospatial tools. Demonstrated via hands-on case studies based on wind speed data of Lagos, Nigeria, it was shown how several ML algorithms, such as Random Forest (RF), Naïve Bayes (NB), XGBoost (XGB), Linear Regression (LR) and Neural Networks (NN), can be utilised to recognise and predict patterns in the environment. The models were validated using Root Mean Square Errors (RMSE) and Mean Absolute Error (MAE).

The IRMA Community

Research IRM

Integration of Machine Learning and AI With Geospatial Analysis

Purchase

Abstract

Related Content

IRMA Sponsors