Modeling land use and land cover changes in a vulnerable coastal region using artificial neural networks and cellular automata

Abstract

As one of the most vulnerable coasts in the continental USA, the Lower Mississippi River Basin (LMRB) region has endured numerous hazards over the past decades. The sustainability of this region has drawn great attention from the international, national, and local communities, wanting to understand how the region as a system develops under intense interplay between the natural and human factors. A major problem in this deltaic region is significant land loss over the years due to a combination of natural and human factors. The main scientific and management questions are what factors contribute to the land use land cover (LULC) changes in this region, can we model the changes, and how would the LULC look like in the future given the current factors? This study analyzed the LULC changes of the region between 1996 and 2006 by utilizing an artificial neural network (ANN) to derive the LULC change rules from 15 human and natural variables. The rules were then used to simulate future scenarios in a cellular automation model. A stochastic element was added in the model to represent factors that were not included in the current model. The analysis was conducted for two sub-regions in the study area for comparison. The results show that the derived ANN models could simulate the LULC changes with a high degree of accuracy (above 92 % on average). A total loss of 263 km(2) in wetlands from 2006 to 2016 was projected, whereas the trend of forest loss will cease. These scenarios provide useful information to decision makers for better planning and management of the region.

Towards an uncertainty reduction framework for land-cover change prediction using possibility theory

“…From these results, we note that the desert land cover in the study area is replaced by residential land (urban land). Knowing the current and estimated urbanization situation will help decision makers to Table 5 Comparaison between real changes and changes prediction for the proposed approach and the proposed approach applied to model described in [40] Urban (%)…”

“…To evaluate the proposed approach in improving LCC prediction, we apply the proposed uncertainty propagation approach on the LCC model described by Qiang and Lam in [40] to the Saint-Denis city, Reunion Island. The LCC prediction model proposed in [40] uses the Artificial Neural Network (ANN) to derive the LCC rules and then applies the Cellular Automate (CA) model to simulate future scenarios.…”

“…The LCC prediction model proposed in [40] uses the Artificial Neural Network (ANN) to derive the LCC rules and then applies the Cellular Automate (CA) model to simulate future scenarios. Table 2 depicts the percentages of change of the five landcover types (water, urban, bare soil, forest, and non-dense vegetation).…”

“…Table 2 depicts the percentages of change of the five landcover types (water, urban, bare soil, forest, and non-dense vegetation). It shows the difference between real changes, predicted changes of the proposed approach, and changes made by the proposed approach applied to model described in [40]. Table 2 Comparison between real changes, predicted changes of the proposed approach, and changes made by the proposed approach applied to model described in [40] Water (%)…”

“…In this case study, we also apply the proposed uncertainty propagation approach on the LCC model described by Qiang and Lam in [40] to the Cairo region, Egypt. Table 5 depicts the percentages of change of the four land-cover types (urban, agriculture, water, and desert).…”