Spatiotemporal Assessment and Machine Learning-Based Future Forecasting of Groundwater Hydro chemical Dynamics and Drawdown Variability DOI

Sheraz Maqbool,

Muhammad Imran Khan,

Aamir Raza

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Сен. 24, 2024

Abstract Pakistan's groundwater resources are vital to the country's water supply, yet increasingly threatened by issues such as over-extraction, inadequate management practices, and insufficient conservation regulations. This study was conducted examine spatiotemporal aquifer behavior, fluctuations in drawdown levels, quality parameters like pH, Electrical Conductivity (EC), Total Dissolved Salts (TDS), Calcium, Magnesium, Hardness (TH), Bicarbonates Chlorides using geospatial techniques address sustainable resource needs. For future forecasting four machine learning (ML) models were used; Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF). Observed data obtained from Water Sanitation Agency (WASA) Faisalabad year 2013 2023 which included 29 inline field area well stations 25 Japan International Cooperation (JICA) stations, weather Terra Climate dataset. Groundwater patterns changes over time analyzed GIS-based spatial analysis utilizing historical train test predictive for 2024-2028. The XGBoost model demonstrated exceptional performance predicting pre-monsoon (8.35m) post-monsoon (7.65m) until 2028 hydro chemical quality, with an average R-squared value of 0.86, RMSE below 0.08, MAE under 0.05 both. study's revealed significant seasonal variations, increases mineral concentrations due intensified leaching processes identified a concerning rise chloride levels after 2022, linked anthropogenic activities. These findings underscored importance advanced techniques, particularly XGBoost, accurately dynamics quality.

Язык: Английский

Optimization of Integrated Operation of Surface and Groundwater Resources using Multi-Objective Grey Wolf Optimizer (MOGWO) Algorithm DOI

Ali Torabi,

Fariborz Yosefvand, Saeid Shabanlou

и другие.

Water Resources Management, Год журнала: 2024, Номер 38(6), С. 2079 - 2099

Опубликована: Фев. 13, 2024

Язык: Английский

Процитировано

10
Towards Groundwater-Level Prediction Using Prophet Forecasting Method by Exploiting a High-Resolution Hydrogeological Monitoring System DOI Open Access
Davide Fronzi, Gagan Narang, Alessandro Galdelli

и другие.

Water, Год журнала: 2023, Номер 16(1), С. 152 - 152

Опубликована: Дек. 30, 2023

Forecasting of water availability has become increasing interest in recent decades, especially due to growing human pressure and climate change, affecting groundwater resources towards a perceivable depletion. Numerous research papers developed at various spatial scales successfully investigated daily or seasonal level prediction starting from measured meteorological data (i.e., precipitation temperature) observed levels, by exploiting data-driven approaches. Barely few combine the variables with unsaturated zone monitored soil content, temperature, bulk electric conductivity), and—in most these—the vadose is only single depth. Our approach exploits high spatial-temporal resolution hydrogeological monitoring system Conero Mt. Regional Park (central Italy) predict trends shallow aquifer exploited for drinking purposes. The field equipment consists thermo-pluviometric station, three volumetric conductivity, temperature probes 0.6 m, 0.9 1.7 respectively, piezometer instrumented permanent water-level probe. period started January 2022, were recorded every fifteen minutes more than one hydrologic year, except which was on scale. model “virtual boxes” atmosphere, zone, saturated zone) hydrological characterizing each box integrated into time series forecasting based Prophet Python environment. Each parameter tested its influence prediction. fine-tuned an acceptable (roughly 20% ahead period). quantitative analysis reveals that optimal results are achieved expoiting collected depth m below ground level, Mean Absolute Error (MAE) 0.189, Percentage (MAPE) 0.062, Root Square (RMSE) 0.244, Correlation coefficient 0.923. This study stresses importance calibrating methods exploring conjunction those data, thus emphasizing role as challenging but vital aspect optimizing management.

Язык: Английский

Процитировано

12
A Hybrid Machine Learning Model for Modeling Nitrate Concentration in Water Sources DOI

Adnan Mazraeh,

Meysam Bagherifar,

Saeid Shabanlou

и другие.

Water Air & Soil Pollution, Год журнала: 2023, Номер 234(11)

Опубликована: Ноя. 1, 2023

Язык: Английский

Процитировано

10
Prediction of groundwater level using GMDH artificial neural network based on climate change scenarios DOI Creative Commons

Ehsan Azizi,

Fariborz Yosefvand, Behrouz Yaghoubi

и другие.

Applied Water Science, Год журнала: 2024, Номер 14(4)

Опубликована: Март 14, 2024

Abstract One of the main challenges regarding prediction groundwater resource changes is climate change phenomenon and its impacts on quantitative variations such resources. Groundwater resources are treated as one strategic any region. Given hydrological parameters, it necessary to evaluate predict future achieve an appropriate plan maintain preserve water In this regard, present study put forward by utilizing Statistical Down-Scaling Model (SDSM) forecast variables (i.e., temperature precipitation) based new Rcp scenarios for greenhouse gas emissions within a period from 2020 2060. The results obtained parameters indicate different values in each emission scenario, so limit, minimum maximum occur Rcp8.5, Rcp2.6 Rcp4.5 scenarios, respectively. Also, model developed GMDH artificial neural network technique. predicts average level way that implementing forecasted SDSM model, time 2060 predicted. verification validation imply proper performance reasonable accuracy predicating variables. findings derived paper compared years prior period, Sahneh Plain has dramatically dropped their lowest state 2046 2056. can be used managers decision makers layout evaluating effects Plain.

Язык: Английский

Процитировано

4
An Adaptive Hybrid (1D-2D) Convolution-Based ShuffleNetV2 Mechanism for Irrigation Levels Prediction in Agricultural Fields With Smart IoTs DOI Creative Commons
Xuehui Xu,

R. S. M. Lakshmi Patibandla,

Amit Arora

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 71901 - 71918

Опубликована: Янв. 1, 2024

Rich natural resources such as fertilizers, environment, groundwater, rivers, and land are abundant in many countries. Agriculture is the primary source of income for people living different There have not been shortages like river water recent decades. But, lack knowledge on how to use those valuable main reason resource wastage. The amount applied crop fields a variety soil, weather, growth stages can be managed optimized using smart farming. field's soil moisture measured sensors positioned at various observation points, which will show much has retained. Unfortunately, farming system capable receive data provided by irrigation management due issues with connectivity or sensor failure. Innovative agricultural approaches facilitated Internet Things (IoT) technologies. These IoT nodes encountered energy limitations challenging routing techniques result their low capacity. Therefore, it imperative resolve implementing an effective IoT-based area. major steps developed model collection prediction. Initially, essential image attained from benchmark resources. Next, collected images level prediction phase. This phase facilitates farmers maximize yields minimize production cost. Here, performed Adaptive Hybrid (1D-2D) Convolution-based ShuffleNetV2 (AHC-ShuffleNetV2). Moreover, parameters suggested AHC-ShuffleNetV2 Fitness-based Piranha Foraging Optimization Algorithm (FPFOA). increases performance rates proposed model. Later, several experimental analyses executed over classical display effectualness rate. When considering sigmoid activation function, implemented framework's RMSE was minimized 73.15% POA-ShuffleNetV2, 72.36% RSA-ShuffleNetV2, 78.94% MRS-ShuffleNetV2, 79.47% PFOA-ShuffleNetV2 respectively. Hence, revealed that designed error also achieved higher efficacy than other baseline techniques.

Язык: Английский

Процитировано

3
Projection of groundwater level fluctuations using deep learning and dynamic system response models in a drought affected area DOI
Dilip Roy,

Chitra Rani Paul,

Md. Panjarul Haque

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(1)

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
An improved support vector machine model for groundwater level prediction: a case study DOI
Sasmita Sahoo, Deba Prakash Satapathy

Earth Science Informatics, Год журнала: 2025, Номер 18(1)

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
An Intelligent Combination of Machine Learning Approaches for Groundwater Fluctuations Prediction DOI

Abbasali Rezapour,

Mostafa Sabzekar

Iranian Journal of Science and Technology Transactions of Civil Engineering, Год журнала: 2025, Номер unknown

Опубликована: Фев. 7, 2025

Язык: Английский

Процитировано

0
Design optimization of dual-circulation wells using deep learning DOI

Yang Sikai,

Fang Zhang,

Yanling Ma

и другие.

Stochastic Environmental Research and Risk Assessment, Год журнала: 2025, Номер unknown

Опубликована: Фев. 26, 2025

Язык: Английский

Процитировано

0
Predicting Groundwater Levels Using Advanced Deep Learning Models: A Case Study of Raipur, India DOI
S. Thakur, Sanjeev Karmakar

Transactions of Indian National Academy of Engineering, Год журнала: 2025, Номер unknown

Опубликована: Май 13, 2025

Язык: Английский

Процитировано

0