Integrating Geo-AI with RS & GIS for comprehensive assessments of urban land cover transformations and integrated responses

Environmental Earth Sciences, Journal Year: 2024, Volume and Issue: 84(1)

Published: Dec. 9, 2024

Language: Английский

---

Forecasting Urban Sprawl Dynamics in Islamabad: A Neural Network Approach

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(3), P. 492 - 492

Published: Jan. 31, 2025

In the past two decades, Islamabad has experienced significant urbanization. As a result of inadequate urban planning and spatial distribution, it significantly influenced land use–land cover (LULC) changes green areas. To assess these changes, there is an increasing need for reliable appropriate information about Landsat imagery categorized into four thematic classes using supervised classification method called support vector machine (SVM): built-up, bareland, vegetation, water. The results change detection post-classification show that city region increased from 6.37% (58.09 km2) in 2000 to 28.18% (256.49 2020, while vegetation decreased 46.97% (428.28 34.77% (316.53 bareland 45.45% (414.37 35.87% (326.49 km2). Utilizing modeler (LCM), forecasts future conditions 2025, 2030, 2035 are predicted. artificial neural network (ANN) model embedded IDRISI software 18.0v based on well-defined backpropagation (BP) algorithm was used simulate sprawl considering historical pattern 2015–2020. Selected landscape morphological measures were quantify analyze structure patterns. According data, area grew at pace 4.84% between 2015 2020 will grow rate 1.47% 2035. This growth metropolitan encroach further bareland. If existing patterns persist over next ten years, drop mean Euclidian Nearest Neighbor Distance (ENN) patches anticipated (from 104.57 m 101.46 2020–2035), indicating accelerated transformation landscape. Future prediction modeling revealed would be huge increase 49% areas until year compared 2000. rapidly urbanizing areas, urgent enhance use laws policies ensure sustainability ecosystem, development, preservation natural resources.

Language: Английский

---

Spatio-temporal analysis of urban expansion and land use dynamics using google earth engine and predictive models

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 27, 2025

Urban expansion and changes in land use/land cover (LULC) have intensified recent decades due to human activity, influencing ecological developmental landscapes. This study investigated historical projected LULC urban growth patterns the districts of Multan Sargodha, Pakistan, using Landsat satellite imagery, cloud computing, predictive modelling from 1990 2030. The analysis images was grouped into four time periods (1990–2000, 2000–2010, 2010–2020, 2020–2030). Google Earth Engine cloud-based platform facilitated classification 5 ETM (1990, 2000, 2010) 8 OLI (2020) Random Forest model. A simulation model integrating Cellular Automata an Artificial Neural Network Multilayer Perceptron MOLUSCE plugin QGIS employed forecast resulting maps showed consistently high accuracy levels exceeding 92% for both across all periods. revealed that Multan's built-up area increased 240.56 km2 (6.58%) 440.30 (12.04%) 2020, while Sargodha experienced more dramatic 730.91 (12.69%) 1,029.07 (17.83%). Vegetation remained dominant but significant variations, particularly peri-urban areas. By 2030, is stabilize at 433.22 km2, primarily expanding southeastern direction. expected reach 1,404.97 showing balanced multi-directional toward northeast north. presents effective analytical method processing, GIS, change modeling evaluate spatiotemporal changes. approach successfully identified main transformations trends areas highlighting potential urbanization zones where opportunities exist developing planned managed settlements.

Language: Английский

---

Modelling sustainable land management programme intervention effect on soil loss rate in the watershed region

Soil Use and Management, Journal Year: 2025, Volume and Issue: 41(1)

Published: Jan. 1, 2025

Abstract This paper modelled the sustainable land management programme intervention effect on soil loss rate in Hoha and Temba watersheds, Western Ethiopia. In area, (SLMP) has been doing many soil–water conservation measurements since 2011. However, an assessment of before after implementation project not yet conducted area because operational issues high costs gathering on‐ground data. Because this, we have developed a Revised Universal Soil Loss Equation (RUSLE) framework fully integrated with geographic information system (GIS) for spatial resolution (30 m) erosion 2010 (before SLMP was implemented area) 2015 2021 (after area). The results showed that mean annual study 13.04, 1.88 2.06 t ha −1 year 9.58, 1.53 1.68 watershed years, 2010, 2021, respectively. line our also indicated increment forest cover reduction bare both watersheds throughout time. terms reduction, significant role through improvement watersheds.

Language: Английский

---

Enhancing soil moisture retrieval in semi-arid regions using machine learning algorithms and remote sensing data

Applied Soil Ecology, Journal Year: 2024, Volume and Issue: 204, P. 105687 - 105687

Published: Oct. 16, 2024

Language: Английский

---