Automatic Impervious Surface Area Detection Using Image Texture Analysis and Neural Computing Models with Advanced Optimizers

Abstract

Up-to-date information regarding impervious surface is valuable for urban planning and management. The objective of this study is to develop neural computing models used for automatic impervious surface area detection at a regional scale. To achieve this task, advanced optimizers of adaptive moment estimation (Adam), a variation of Adam called Adamax, Nesterov-accelerated adaptive moment estimation (Nadam), Adam with decoupled weight decay (AdamW), and a new exponential moving average variant (AMSGrad) are used to train the artificial neural network models employed for impervious surface detection. These advanced optimizers are benchmarked with the conventional gradient descent with momentum (GDM). Remotely sensed images collected from Sentinel-2 satellite for the study area of Da Nang city (Vietnam) are used to construct and verify the proposed approach. Moreover, texture descriptors including statistical measurements of color channels and binary gradient contour are employed to extract useful features for the neural computing model-based pattern recognition. Experimental result supported by statistical test points out that the Nadam optimizer-based neural computing model has achieved the most desired predictive accuracy for the data collected in the studied region with classification accuracy rate of 97.331%, precision = 0.961, recall = 0.984, negative predictive value = 0.985, and F1 score = 0.972. Therefore, the model developed in this study can be a helpful tool for decision-makers in the task of urban land-use planning and management.

RETRACTED ARTICLE: Artificial intelligence assisted Internet of Things based financial crisis prediction in FinTech environment

“…The Nadam optimizer explained in Dozat (2016), tries to integrate Nesterov-accelerated adaptive moment estimation as to Adam. The main benefit of this combined model is that utilized adaptive moment estimation uses for performing extremely accurate steps from gradient direction using upgrades of model parameter through the momentum step previously the calculation of gradient (Hoang, 2021). The upgrade rule of Nadam is expressed as:…”

Intrusion detection system using metaheuristic fireworks optimization based feature selection with deep learning on Internet of Things environment

“…At last, the hyperparameters of DRNN are ideally chosen through the Nadam optimizer. The Nadam optimization is the incorporation of Nesterov‐accelerated adaptive moment estimation and Adam (Hoang, 2021). The gain of this combined technique is that the adaptive moment estimation used in it is used to implement highly accurate steps from the gradient direction.…”

A Novel Deep Learning Approach to Malaria Disease Detection on Two Malaria Datasets

“…The Adamax optimization method is a variation of the Adam optimization method, which has update rules to weight the models. Proportional scales the 𝐿 𝑝 norm of gradients from the current and previous networks [29]. Equation 21shows the weight update according to the Adamax optimization method.…”

“…Nesterov-Accelerated Adaptive Moment Estimation (Nadam) is calculated by integrating adaptive moment estimation into the optimization method Adam optimization method calculation formula [29]. It ensures that the specified insertion gradient value achieves high accuracy.…”