Novel Encoder–Decoder Architecture with Attention Mechanisms for Satellite-Based Environmental Forecasting in Smart City Applications

Guardat en:

Dades bibliogràfiques
Publicat a:	Future Internet vol. 17, no. 9 (2025), p. 380-412
Autor principal:	Panhwar Kalsoom
Altres autors:	Soomro Bushra Naz, Bhatti Sania, Jaskani Fawwad Hassan
Publicat:	MDPI AG
Matèries:	Pakistan China Accuracy Temporal resolution Desertification Internet Deep learning Image resolution Computer architecture Early warning systems Environmental monitoring Optimization techniques Artificial neural networks Satellite imagery Edge computing Architecture Data integration Machine learning Monitoring systems Coders Smart cities Environmental management Vegetation Remote sensing Earth observations (from space) Artificial intelligence Infrastructure Design Algorithms Literature reviews Satellite observation Real time Cloud computing Forecasting
Accés en línia:	Citation/Abstract Full Text + Graphics Full Text - PDF
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!

Descripció
Resum:	Desertification poses critical threats to agricultural productivity and socio-economic stability, particularly in vulnerable regions like Thatta and Badin districts of Sindh, Pakistan. Traditional monitoring methods lack the accuracy and temporal resolution needed for effective early warning systems. This study presents a novel Spatio-Temporal Desertification Predictor (STDP) framework that integrates deep learning with next-generation satellite imaging for time-series desertification forecasting. The proposed encoder–decoder architecture combines Convolutional Neural Networks (CNNs) for spatial feature extraction from high-resolution satellite imagery with modified Long Short-Term Memory (LSTM) networks enhanced by multi-head attention to capture temporal dependencies. Environmental variables are fused through an adaptive data integration layer, and hyperparameter optimization is employed to enhance model performance for edge computing deployment. Experimental validation on a 15-year satellite dataset (2010–2024) demonstrates superior performance with MSE = 0.018, MAE = 0.079, and <inline-formula>R2=0.94</inline-formula>, outperforming traditional CNN-only, LSTM-only, and hybrid baselines by 15–20% in prediction accuracy. The framework forecasts desertification trends through 2030, providing actionable signals for environmental management and policy-making. This work advances the integration of AI with satellite-based Earth observation, offering a scalable path for real-time environmental monitoring in IoT and edge computing infrastructures.
ISSN:	1999-5903
DOI:	10.3390/fi17090380
Font:	ABI/INFORM Global