Enhancement of land-use change modeling using convolutional neural networks and convolutional denoising autoencoders

TL;DR

This paper introduces hybrid convolutional neural network models, including a CNN and a convolutional denoising autoencoder, to improve land-use change prediction from satellite images, demonstrating enhanced performance over traditional models.

Contribution

The study develops novel hybrid CNN and CDAE-net models that incorporate neighborhood effects and denoising capabilities for improved land-use change modeling.

Findings

Conv-net outperforms CDAE-net in predictive accuracy.

Models with satellite image features outperform those with only geographical data.

CDAE-net performs better with noisy data.

Abstract

The neighborhood effect is a key driving factor for the land-use change (LUC) process. This study applies convolutional neural networks (CNN) to capture neighborhood characteristics from satellite images and to enhance the performance of LUC modeling. We develop a hybrid CNN model (conv-net) to predict the LU transition probability by combining satellite images and geographical features. A spatial weight layer is designed to incorporate the distance-decay characteristics of neighborhood effect into conv-net. As an alternative model, we also develop a hybrid convolutional denoising autoencoder and multi-layer perceptron model (CDAE-net), which specifically learns latent representations from satellite images and denoises the image data. Finally, a DINAMICA-based cellular automata (CA) model simulates the LU pattern. The results show that the convolutional-based models improve the modeling performances compared with a model that accepts only the geographical features. Overall, conv-net outperforms CDAE-net in terms of LUC predictive performance. Nonetheless, CDAE-net performs better when the data are noisy.