
Research Square (Research Square), Год журнала: 2024, Номер unknown
Опубликована: Июнь 20, 2024
Язык: Английский
Research Square (Research Square), Год журнала: 2024, Номер unknown
Опубликована: Июнь 20, 2024
Язык: Английский
MethodsX, Год журнала: 2024, Номер 12, С. 102757 - 102757
Опубликована: Май 31, 2024
Язык: Английский
Процитировано
21Results in Engineering, Год журнала: 2024, Номер unknown, С. 102997 - 102997
Опубликована: Сен. 1, 2024
Язык: Английский
Процитировано
16Physics and Chemistry of the Earth Parts A/B/C, Год журнала: 2024, Номер 134, С. 103563 - 103563
Опубликована: Янв. 28, 2024
Язык: Английский
Процитировано
6Water, Год журнала: 2024, Номер 16(10), С. 1423 - 1423
Опубликована: Май 16, 2024
In South China, the large quantity of rainfall in pre-summer rainy season can easily lead to natural disasters, which emphasizes importance improving accuracy precipitation forecasting during this period for social and economic development region. paper, back-propagation neural network (BPNN) is used establish model forecasting. Three schemes are applied improve performance: (1) predictors selected based on individual meteorological stations within region rather than as a whole; (2) triangular irregular (TIN) proposed preprocess observed data input BPNN model, while simulated/forecast expected output; (3) genetic algorithm hyperparameter optimization BPNN. The first scheme reduces mean absolute percentage error (MAPE) root square (RMSE) simulation by roughly 5% more 15 mm; second MAPE RMSE 15% mm, respectively, third improves inapparently. Obviously, raises upper limit capability greatly preprocessing data. During training validation periods, improved be controlled at approximately 35%. For hindcasting test period, anomaly rate less 50% only one season, highest 64.5%. According correlation coefficient Ps score hindcast precipitation, performance slightly better FGOALS-f2 model. Although global climate change makes variable, trend almost identical that values over whole suggesting able capture general characteristics change.
Язык: Английский
Процитировано
4Environmental earth sciences, Год журнала: 2025, Номер unknown, С. 171 - 180
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
0Rendiconti lincei. Scienze fisiche e naturali, Год журнала: 2024, Номер unknown
Опубликована: Окт. 18, 2024
Язык: Английский
Процитировано
2Revista de Gestão Social e Ambiental, Год журнала: 2024, Номер 18(6), С. e08267 - e08267
Опубликована: Авг. 1, 2024
Objective: The objective of the research was to analyze and compare different machine learning models identify which technique presents best performance in predicting hydrometeorological variables. Theoretical Framework: This section main concepts that underpin work. Machine techniques such as support vector machines, decision trees, random forests, artificial neural networks, gradient boosting are presented, providing a solid foundation for understanding context investigation. Method: study uses comparative methodology by applying predict variables based on data collected Petrolina-PE. Various were employed compared. Data normalization performed through logarithms, treatment included filling or excluding inconsistent records. effectiveness is evaluated using metrics Nash-Sutcliffe efficiency coefficient, Willmott index, Pearson correlation coefficient. Results Discussion: obtained results showed good predictability, ranging from 50 70% efficiency. analysis allowed identifying patterns relationships between initial configurations algorithms, contributing better processes their predictability. Research Implications: By more accurate reliable forecasts, presented can assist managers making decisions about sustainable use water mitigation natural disasters floods. Originality/Value: contributes literature advancing estimation variables, improving existing techniques, resource management. Its impact extends mitigating risks associated with extreme hydrological events promoting resources, sustainability resilience aquatic ecosystems, essential face climate change environmental challenges.
Язык: Английский
Процитировано
1Journal of Environmental and Agricultural Studies, Год журнала: 2024, Номер 5(3), С. 23 - 34
Опубликована: Ноя. 9, 2024
The key aim of this research project is to design and evaluate advanced machine learning models for increasing accuracy in rainfall forecasting over the USA. We intended investigate nonlinear relationships typical atmospheric variables using state-of-the-art ML methods more accurate predictions. For on USA, we utilized an extensive dataset that comprises historical data collected from National Oceanic Atmospheric Administration (NOAA) other meteorological agencies. main use paper consists daily measurements across various geographical locations thus capturing wide-ranging necessary both training validation model. Besides measuring rainfall, included sources such as NOAA's Global Historical Climatology Network NASA's Modern-Era Retrospective Analysis Research Applications. These datasets further provided are known affect rain, including temperature, humidity, wind speed, pressure. performance metrics used work considered include accuracy, precision, recall, F1 score. above table shows Random Forest Classifier outperformed models, achieving perfect accuracy. That indicated it rightly classified all instances test set. Logistic Regression Support Vector Machine gave a quite good by giving average but had lower precision recall prediction. Accurate has direct consequences agriculture, greatly empowering farmers agricultural planners make effective decisions regarding planting, harvesting, crop management. forecasts also critical importance disaster management planning flood emergencies. Moreover, precise particularly sustainable water resources management, presents most important conserving these resources.
Язык: Английский
Процитировано
1Ecological Engineering & Environmental Technology, Год журнала: 2024, Номер 25(7), С. 1 - 10
Опубликована: Май 20, 2024
The study discussed the change in amounts of rainfall falling on two governorates Iraq, one north and other south, differing topographic elevation.The descriptive analytical approach, drawing inferential maps, adopting a digital elevation model were used to prove results.The aimed identify effect terrain factor increasing precipitation.Rainfall its decrease with sea level areas emerges importance using (DEM) as an analysis tool building three-dimensional models phenomena give comprehensive survey Earth's surface, this turn enhances accuracy extracted results well demonstrating capabilities inherent geographic information system (GIS) program dealing input analysis.And processing outputting quantitative data.The most important are that highest rainfall, rain reaching more than 360 mm, correspond terrain, which reaches height 1800 meters above level, represented Aqra Mountains Al-Sheikhan Sinjar Makhmour, within Nineveh Governorate.In second area, Basra Governorate, we find located desert range Western Plateau Hafr Al-Batin Valley approximately 290 m, it is land lime, gravel, sand.Thus, originality scientific fact becomes clear us, values these Its averages do not exceed 182 anomaly precipitation has become clear, low-lying exposed crossed by high contour line, due rocky limestone formation, tongue Iraqi region, adjacent both states Kuwait Saudi Arabia.The value comes from obtained showing eroding, difference (two governorates) Mosul, mountainous nature, eroding surface features low land, role modern technologies highlighting rates both.
Язык: Английский
Процитировано
0Research Square (Research Square), Год журнала: 2024, Номер unknown
Опубликована: Июнь 20, 2024
Язык: Английский
Процитировано
0