Land use/land cover prediction and analysis of the middle reaches of the Yangtze River under different scenarios

The Science of The Total Environment, Journal Year: 2022, Volume and Issue: 833, P. 155238 - 155238

Published: April 13, 2022

Language: Английский

---

Analysing land use/land cover changes and its dynamics using remote sensing and GIS in Gubalafito district, Northeastern Ethiopia

SN Applied Sciences, Journal Year: 2021, Volume and Issue: 4(1)

Published: Dec. 20, 2021

Abstract Mapping and quantifying the status of Land use/Land cover (LULC) changes drivers change are important for identifying vulnerable areas designing sustainable ecosystem services. This study analyzed LULC key last 30 years through a combination remote sensing GIS with surveying local community understanding patterns in Gubalafto district, Northeastern Ethiopia. Five major types (cultivated settlement, forest cover, grazing land, bush land bare land) from Landsat images 1986, 2000, 2016 were mapped. The results demonstrated that cultivated settlement constituted most extensive type area increased by 9% extent. It also revealed substantial expansion during past years. On other hand, classes has high environmental importance such as have reduced drastically time expanding same period. 1986 was about 11.1% total area, it had decreased to 5.7% 2016. In contrast, 45.6% 49.5% Bush 14.8 21% period, while declined 8.9 2% root causes this particular include population growth, tenure insecurity, common property rights, persistent poverty, climate change, lack public awareness. Therefore, be controlled, resources use is essential; else, these scarce natural resource bases will soon lost no longer able play their contribution Article Highlights Forest lands rapidly. Fluctuating trends land. Population pressure associated demand main behind area.

Language: Английский

---

Impact of Urbanization on Urban Heat Island Intensity in Major Districts of Bangladesh Using Remote Sensing and Geo-Spatial Tools

Climate, Journal Year: 2022, Volume and Issue: 10(1), P. 3 - 3

Published: Jan. 4, 2022

Urbanization is closely associated with land use cover (LULC) changes that correspond to surface temperature (LST) variation and urban heat island (UHI) intensity. Major districts of Bangladesh have a large population base commonly lack the resources manage fast urbanization effects, so any rise in influences both directly indirectly. However, little known about impact rapid on UHI intensity variations during winter dry period major Bangladesh. To this end, we aim quantify spatiotemporal associations between 2000 2019 using remote-sensing geo-spatial tools. Landsat-8 Landsat-5 imageries these from 2020 were used for purpose, overall precision varying 81% 93%. The results LULC classification LST estimation showed existence multiple UHIs all districts, which upward trends, except Rajshahi Rangpur districts. A substantial increase expansion was observed Barisal > 32%, Mymensingh 18%, Dhaka 17%, Chattogram 14%, 13%, while significant decrease built-up areas noticed Sylhet < −1.45% −3.72%. We found greater than small High intensities 10 °C, 9 8 °C compared other due dense unplanned urbanization. identified higher (hotspots) zones be increased bare land. suburbanized strategy should prioritize restraint high UHIs. heterogeneous over seven found, might potential implications regional climate change. Our study findings will enable policymakers reduce change effect concerned

Language: Английский

---

Exploring forest fire susceptibility and management strategies in Western Himalaya: Integrating ensemble machine learning and explainable AI for accurate prediction and comprehensive analysis

Environmental Technology & Innovation, Journal Year: 2024, Volume and Issue: 35, P. 103655 - 103655

Published: May 5, 2024

Forest fires pose a significant threat to ecosystems and socio-economic activities, necessitating the development of accurate predictive models for effective management mitigation. In this study, we present novel machine learning approach combined with Explainable Artificial Intelligence (XAI) techniques predict forest fire susceptibility in Nainital district. Our innovative methodology integrates several robust — AdaBoost, Gradient Boosting Machine (GBM), XGBoost Random Deep Neural Network (DNN) as meta-model stacking framework. This not only utilises individual strengths these models, but also improves overall prediction performance reliability. By using XAI techniques, particular SHAP (SHapley Additive exPlanations) LIME (Local Interpretable Model-agnostic Explanations), improve interpretability provide insights into decision-making processes. results show effectiveness ensemble model categorising different zones: very low, moderate, high high. particular, identified extensive areas susceptibility, precision, recall F1 values underpinning their effectiveness. These achieved ROC AUC above 0.90, performing exceptionally well an 0.94. The are remarkably inclusion confidence intervals most important metrics all emphasises robustness reliability supports practical use management. Through summary plots, analyze global variable importance, revealing annual rainfall Evapotranspiration (ET) key factors influencing susceptibility. Local analysis consistently highlights importance rainfall, ET, distance from roads across models. study fills research gap by providing comprehensive interpretable modelling that our ability effectively manage risk is consistent environmental protection sustainable goals.

Language: Английский

---

Prediction of land use for the next 30 years using the PLUS model's multi-scenario simulation in Guizhou Province, China

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 7, 2024

Abstract Land use changes significantly impact the structure and functioning of ecosystems. The current research focus lies in how to utilize economic policy instruments regulate conflicts among stakeholders effectively. objective is facilitate rational planning sustainable development land utilization resources. PLUS model integrates a rule-based mining method for expansion analysis CA based on multi-type stochastic seeding mechanism, which can be used mine driving factors predict patch-level evolution landscapes. Using model, simulation was conducted study future distribution area over next 30 years. Based data from Guizhou Province 2000, 2010, 2020, total 16 were selected three aspects: geographical environment, transportation network, socio-economic conditions. Four scenarios, namely natural development, urban ecological conservation, farmland rotection, established. Comparative simulated differences various scenarios performed. (1) overall accuracy using 0.983, with Kappa coefficient 0.972 FoM 0.509. meets requirements. (2) Through four different investigated Each scenario exhibited distinct impacts utilization. Comprehensive comparison results revealed that protection aligns goals area. Currently, there relative scarcity simulation, particularly application, Province. This aims provide reference resources high-quality construction Guizhou, promoting tandem advanced environmental protection.

Language: Английский

---

Fault Prediction Based on Leakage Current in Contaminated Insulators Using Enhanced Time Series Forecasting Models

Sensors, Journal Year: 2022, Volume and Issue: 22(16), P. 6121 - 6121

Published: Aug. 16, 2022

To improve the monitoring of electrical power grid, it is necessary to evaluate influence contamination in relation leakage current and its progression a disruptive discharge. In this paper, insulators were tested saline chamber simulate increase salt on their surface. From time series forecasting current, possible development fault before flashover occurs. for complete evaluation, long short-term memory (LSTM), group method data handling (GMDH), adaptive neuro-fuzzy inference system (ANFIS), bootstrap aggregation (bagging), sequential learning (boosting), random subspace, stacked generalization (stacking) ensemble models are analyzed. results best structure models, hyperparameters evaluated wavelet transform used obtain an enhanced model. The contribution paper related improvement well-established using transform, thus obtaining hybrid that can be several applications. showed leads all especially ANFIS model, which had mean RMSE 1.58 ×10-3, being model result. Furthermore, standard deviation 2.18 ×10-19, showing stable robust application under study. Future work performed other components distribution grid susceptible because they installed outdoors.

Language: Английский

---

Hydrogeochemical characterization based water resources vulnerability assessment in India's first Ramsar site of Chilka lake

Marine Pollution Bulletin, Journal Year: 2022, Volume and Issue: 184, P. 114107 - 114107

Published: Sept. 11, 2022

Language: Английский

---

A coupled novel framework for assessing vulnerability of water resources using hydrochemical analysis and data-driven models

Journal of Cleaner Production, Journal Year: 2022, Volume and Issue: 336, P. 130407 - 130407

Published: Jan. 6, 2022

Language: Английский

---

Estimating ground-level PM2.5 using subset regression model and machine learning algorithms in Asian megacity, Dhaka, Bangladesh

Air Quality Atmosphere & Health, Journal Year: 2023, Volume and Issue: 16(6), P. 1117 - 1139

Published: Feb. 25, 2023

Language: Английский

---

Evaluation and mapping of predicted future land use changes using hybrid models in a coastal area

Ecological Informatics, Journal Year: 2023, Volume and Issue: 78, P. 102324 - 102324

Published: Oct. 2, 2023

Language: Английский

---