A comprehensive evaluation of OPTICS, GMM and K-means clustering methodologies for geochemical anomaly detection connected with sample catchment basins

Geochemistry, Journal Year: 2024, Volume and Issue: 84(2), P. 126094 - 126094

Published: Feb. 23, 2024

Language: Английский

---

Assessment and prediction of meteorological drought using machine learning algorithms and climate data

Climate Risk Management, Journal Year: 2024, Volume and Issue: 45, P. 100630 - 100630

Published: Jan. 1, 2024

Monitoring drought in semi-arid regions due to climate change is of paramount importance. This study, conducted Morocco's Upper Drâa Basin (UDB), analyzed data spanning from 1980 2019, focusing on the calculation indices, specifically Standardized Precipitation Index (SPI) and Evapotranspiration (SPEI) at multiple timescales (1, 3, 9, 12 months). Trends were assessed using statistical methods such as Mann-Kendall test Sen's Slope estimator. Four significant machine learning (ML) algorithms, including Random Forest, Voting Regressor, AdaBoost K-Nearest Neighbors evaluated predict SPEI values for both three 12-month periods. The algorithms' performance was measured indices. study revealed that distribution within UDB not uniform, with a discernible decreasing trend values. Notably, four ML algorithms effectively predicted specified demonstrated highest Nash-Sutcliffe Efficiency (NSE) values, ranging 0.74 0.93. In contrast, algorithm produced range 0.44 0.84. These research findings have potential provide valuable insights water resource management experts policymakers. However, it imperative enhance collection methodologies expand measurement sites improve representativeness reduce errors associated local variations.

Language: Английский

---

Prediction of surface urban heat island based on predicted consequences of urban sprawl using deep learning: A way forward for a sustainable environment

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2024, Volume and Issue: 135, P. 103682 - 103682

Published: July 23, 2024

Language: Английский

---

Assessing intra and interannual variability of water quality in the Sundarban mangrove dominated estuarine ecosystem using remote sensing and hybrid machine learning models

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 442, P. 140889 - 140889

Published: Jan. 26, 2024

Language: Английский

---

Modeling and Estimating the Land Surface Temperature (LST) Using Remote Sensing and Machine Learning (Case Study: Yazd, Iran)

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(3), P. 454 - 454

Published: Jan. 24, 2024

The pressing issue of global warming is particularly evident in urban areas, where thermal islands amplify the effect. Understanding land surface temperature (LST) changes crucial mitigating and adapting to effect heat islands, ultimately addressing broader challenge warming. This study estimates LST city Yazd, Iran, field high-resolution image data are scarce. assessed through parameters (indices) available from Landsat-8 satellite images for two contrasting seasons—winter summer 2019 2020, then it estimated 2021. modeled using six machine learning algorithms implemented R software (version 4.0.2). accuracy models measured root mean square error (RMSE), absolute (MAE), logarithmic (RMSLE), standard deviation different performance indicators. results show that gradient boosting model (GBM) algorithm most accurate estimating LST. albedo NDVI features with greatest impact on both (with 80.3% 11.27% importance) winter 72.74% 17.21% importance). 2021 showed acceptable seasons. GBM each seasons useful modeling based learning, support decision-making related spatial variations temperatures. method developed can help better understand island mitigation strategies improve human well-being enhance resilience climate change.

Language: Английский

---

Urban engineering insights: Spatiotemporal analysis of land surface temperature and land use in urban landscape

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 92, P. 273 - 282

Published: March 7, 2024

In the field of urban environment engineering, understanding relationship between land surface temperature (LST) and use cover (LULC) is essential in rapidly growing climatically unstable landscapes such as Chengdu. It helps alleviate magnitude intensity Urban Heat Islands (UHIs). Toward this aim, summer winter Landsat images were acquired four years from 1992 to 2021 used extract LULC classes, LST three indices Normalized Difference Vegetation Index (NDVI), Built-up (NDBI), Modified Water (MNDWI) analyze their spatiotemporal associations. Results showed that built-up areas expanded approximately six times (820.82 Km2, 584.96%) 2021. Meanwhile, mean increased both seasons, by 9.94 °C 0.95 winter. The LST-NDBI correlation was significant positive studied (0.437< r <0.874, p=0.00) while a very high variability observed LST-NDVI (-0.835< <0.255, LST-MNDWI (-0.632< <0.628, coefficients. According results, NDBI can be good intra- inter-annual predictor Chengdu, especially context its fast-paced physical expansion increasing UHI.

Language: Английский

---

Advanced stacked integration method for forecasting long-term drought severity: CNN with machine learning models

Journal of Hydrology Regional Studies, Journal Year: 2024, Volume and Issue: 53, P. 101759 - 101759

Published: April 11, 2024

Eight governorates in upper Egypt namely Aswan, Asyut, Beni-Suef, Fayoum, Luxor, Minya, Qena and Sohag. This study aims to develop novel hybrid machine learning (ML) models for forecasting the drought phenomena based on limited inputs eight Egyptian govern-orates, ii) evaluate performance accuracy of developed ML predicting Palmer Drought Severity Index (PDSI) recommend optimal model statistical metrics. The were Convolution Neural Networks (CNN)-Long Short-Term Memory (LSTM), CNN-Random Forest (RF), CNN-Support Vector Machine (SVR), CNN-Extreme Gradient Boosting (XGB). Results showed that CNN-LSTM outperformed others followed by CNN-RF. Values NSE, MAE, MARE, IA, R2, RMSE 0.885, 0.915, − 2.073, 0.967, 0.573, respectively. For testing stage CNN-SVR was found perform best; average values 0.828, 0.364, 2.903, 0.950, 0.828 0.688, provided a way forward convenient estimation PDSI from meteorological data terms advancing deep algorithms. models, more or less, can satisfactory predict values. Additionally, suggests as most suitable advance future investigation area.

Language: Английский

---

Assessment of groundwater potential zone mapping for semi-arid environment areas using AHP and MIF techniques

Environmental Sciences Europe, Journal Year: 2024, Volume and Issue: 36(1)

Published: April 29, 2024

Abstract Groundwater resources are essential for drinking water, irrigation, and the economy mainly in semiarid environments where rainfall is limited. Currently, unpredictable due to climate change pollution on Earth’s surface directly affects groundwater resources. In this area, most people depend irrigation purposes, every summer, of area depends a environment. Hence, we selected two popular methods, analytical hierarchy process (AHP) multiple influence factor (MIF) which can be applied map potential zones. Nine thematic layers, such as land use cover (LULC), geomorphology, soil, drainage density, slope, lineament elevation, level, geology maps, were study using remote sensing geographic information system (GIS) techniques. These layers integrated ArcGIS 10.5 software with help AHP MIF methods. The zones revealed four classes, i.e., poor, moderate, good, very based MF zone 241.50 (ha) Poor, 285.64 408.31 92.75 good method. Similarly, method that classes divided into classes: 351.29 511.18 (ha), 123.95 41.78 good. results compared determine methods best planning water resource development specific areas have basaltic rock drought conditions. Both maps validated yield data. receiver operating characteristic (ROC) curve under (AUC) model found 0.80 (good) 0.93 (excellent) respectively; hence, delineation planning. present study’s framework will valuable improving efficiency conserving rainwater maintaining ecosystem India.

Language: Английский

---

Impact assessment of agricultural droughts on water use efficiency in different climatic regions of Punjab Province Pakistan using MODIS time series imagery

Hydrological Processes, Journal Year: 2024, Volume and Issue: 38(7)

Published: July 1, 2024

Abstract Drought is the most destructive phenomenon that distresses terrestrial carbon cycle balance and crop production. The variation in evapotranspiration (ET) gross primary productivity (GPP) a significant cause of agricultural drought effects on water use efficiency. This study aims to evaluate impact WUE it's anomalies different climate regions. standard vegetation index was used measure extent drought. calculated using ratio ET, GPP, classification De Martonne method. conducted over last 22 years, from 2001 2022. Meanwhile, 2001, 2002, 2014, 2018 were considered high years based 22‐year analysis. According remote sensing analysis ET increased throughout all regions more strongly arid zone than humid Humid areas vital due ones. badge with severity across climates except very zone. saw faster recovery times ones, experienced severe droughts. findings this research are essential for understanding cycles agriculture management. helped analyse varying change. significance includes informing agricultural, resource, management planning Punjab Province, an region vulnerable holds important learnings worldwide. It has practical scientific importance regarding systems' specific stresses responses

Language: Английский

---

Evaluation of Land Use Land Cover Changes in Response to Land Surface Temperature With Satellite Indices and Remote Sensing Data

Rangeland Ecology & Management, Journal Year: 2024, Volume and Issue: 96, P. 183 - 196

Published: Aug. 2, 2024

Language: Английский

---