Siamese-LSTM: A predictive model for predicting green space of a location through historical image analysis

Recent statistics reveal a rapid decline in green spaces due to urbanization, impacting both urban and forested areas. Neglecting environmental concerns in urban planning has led to the need to restore greenery in communities. Hence, the objective of this research is to develop a predictive system using deep learning models to forecast changes in green spaces of a specific location over time, contributing to offering insights into urban planning and environmental conservation. Five time series model were explored to predict the change in green space of a location in future, with Long Short-Term Memory (LSTM) demonstrating superior performance. Furthermore, a two-module Siamese-LSTM framework was proposed to forecast future Green View Index (GVI) differences between consecutive years with an i-year gap. The proposed two-module Siamese-LSTM framework predicts the change in a location’s future green view index consisting of individual Siamese Models and an LSTM Model, achieving promising results with an MAE of 0.271, MSE of 0.150 and MAPE of 0.1989.