Projection of Agricultural Land Changes Using Hybrid Cellular Automata and Machine Learning: A Case Study of Babil, Central Iraq

This research aimed to study mapping of agricultural lands, assess their changes, and predict their future scenario in Al-Hillah, Babylon province, Iraq during 2000-2021. The main objectives of the research include developing classification models based on machine learning, analyzing changes of agricultural lands using statistical methods, and predicting future change scenario using a hybrid Cellular Automata (CA) and machine learning model. To improve the accuracy of prediction, this research integrated several driving forces with the historical agricultural land maps to perform the prediction task. The main datasets used for this research were Landsat TM, ETM, and OLI images, as well as several Geographic Information System (GIS) layers including digital elevation model, waterways, population density and vegetation indices. The results indicated that KNN is the best classification as it performed better than the three models. KNN achieved an OA of 0.954, 0.956, and 0.966 for the image data 2000, 2008, and 2021, respectively. Optimizing models’ hyperparameters yielded better classification accuracies in many occasions except SVM for the image data 2000 and KNN for the image data 2021. The assessment of spatial distribution of urban and agricultural lands showed that urban area growth was centric outwards from the city center and the latter expanded to encompass the surrounding areas from 2000 to 2021. The projection of agricultural change demonstrated that agricultural lands in 2034 is expected to be 357.6 km2.

Projection of Agricultural Land Changes Using Hybrid Cellular Automata and Machine Learning: A Case Study of Babil, Central Iraq Keywords:

GIS , LcLu , Remote Sensing , CA , Iraq