Assessing rainfall prediction models: Exploring the advantages of machine learning and remote sensing approaches

Alexandria Engineering Journal, Journal Year: 2023, Volume and Issue: 82, P. 16 - 25

Published: Sept. 29, 2023

Using a comparison of three different major types, the best predictive model was determined. Statistical models and machine learning algorithms automatically learn improve based on data. Deep uses neural networks to complex data patterns relationships. A combination satellite imagery, radar data, ground-based observations are used using aircraft or satellites, remote sensing (RS) collects distant objects locations. Satellites gather regional precipitation for hybrid models. An algorithm trained historical rainfall measurements would then process monitoring instrument input features, machine-learning can predict precipitation. Evaluation regression methods is degree agreement between predicted observed values. The RMSE, R2, MAE statistical measures check precision prediction forecasting model. Machine excels at regardless climate timescale. As one more popular predicting rainfall, LSTM demonstrate their superiority. Remote should be investigated further due scarcity.

Language: Английский

---

A comprehensive review of machine vision systems and artificial intelligence algorithms for the detection and harvesting of agricultural produce

Scientific African, Journal Year: 2023, Volume and Issue: 21, P. e01798 - e01798

Published: July 7, 2023

Every nation's economic development depends heavily on agriculture. Fulfilling the current population's need for food is becoming increasingly difficult because of factors including population growth, frequent climate change, and a lack resources. However, agriculture sector's biggest problems are trained workers, urbanization, available labour. Automation in essential to provide food, fibre, fuels rapidly growing population. Since harvesting critical step farming, authors present systematic review machine vision systems artificial intelligence algorithms detecting agricultural produce this article. The areas that being concentrated include systems, sensors, different image processing utilized detection harvesting. Review various types sensors used automated It demonstrates how several 3D methods, which were obtain position, orientation, point cloud fruit or crop, function compare them. Furthermore, it compares deployed precision This article shows knowledge-based can boost quality.

Language: Английский

---

Modelling monthly rainfall of India through transformer-based deep learning architecture

Modeling Earth Systems and Environment, Journal Year: 2024, Volume and Issue: 10(3), P. 3119 - 3136

Published: Feb. 8, 2024

Language: Английский

---

Comparative analysis of different rainfall prediction models: A case study of Aligarh City, India

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102093 - 102093

Published: April 5, 2024

This research paper delves into creating and comparing rainfall prediction models, employing diverse machine learning algorithms, including Logistic Regression, Decision Tree Classifier, Multi-Layer Perceptron classifier (neural network), Random Forest. The study aims not only to predict patterns but also evaluate the performance of each model through metrics such as Accuracy, Cohen's kappa coefficient, Receiver Operating Characteristic (ROC) curve analysis. Additionally, relevance predictors employed in is thoroughly assessed. results extensive experimentation analysis reveal that Regression (Accuracy = 82.80 %, ROC 82.45 Kappa 65.05 %) Neural Network 82.59 81.94 64.40 has emerged most promising approach, achieving highest percentage accuracy, metrics; among models considered. outcome underscores effectiveness architectures capturing intricate relationships within data.

Language: Английский

---

Prediction of monthly precipitation using various artificial models and comparison with mathematical models

Environmental Science and Pollution Research, Journal Year: 2023, Volume and Issue: 30(14), P. 41209 - 41235

Published: Jan. 11, 2023

Language: Английский

---

Hybrid machine learning and deep learning models for multi-step-ahead daily reference evapotranspiration forecasting in different climate regions across the contiguous United States

Agricultural Water Management, Journal Year: 2023, Volume and Issue: 283, P. 108311 - 108311

Published: April 13, 2023

The daily reference evapotranspiration (ETo) must be accurately forecasted to improve real-time irrigation scheduling and decision-making for water resources allocation. In this study, multi-step (i.e., 1, 3, 7, 10)-ahead ETo at 30 sites is using three hybrid machine learning approaches: wavelet long short-term memory (WLSTM), group method of data handling (WGMDH), genetic algorithm-adaptive neuro-fuzzy inference system (WGA-ANFIS). are chosen sample nine climate regions across the contiguous United States. Three input scenarios considered. This study emphasizes on forecasting limited meteorological variables. first scenario, we consider only solar radiation (Rs) as variable owing largest correlation coefficient (R) between Rs compared with other variables in most sites. second addition Rs, maximum (Tx), minimum (Tn), mean (Tm) air temperatures used. third scenario Tx, Tn, Tm, relative humidity (RH). Data pertaining 2005–2014 2015–2019 used training phases, respectively. model forecasts against estimates from Penman–Monteith (PM) equation. yields accurate results based average over all WLSTM outperforms models 1-day-ahead terms 30-site root square error (RMSE) = 0.541 mm/d, Nash–Sutcliffe (NS) 0.946, R 0.973. contrast, WGMDH WGAANFIS 3-, 7-, 10-day-ahead RMSEs 0.636, 0.649, 0.651 mm/d; NS 0.925,0.922, 0.921; 0.962, 0.961, 0961, highest performances observed Northwest West regions, which exhibit strongest ETo. accuracy decreases South region weakest lowest values Tm RH winter. Consequently, among seasons, RMSE (highest R) worst performance summer, involves Tm. deteriorated warm months attributable high values, cannot capture peaks Deep WGMDH) yield more can thus facilitate agricultural management scheduling.

Language: Английский

---

Particle Swarm Optimized Deep Learning Models for Rainfall Prediction: A Case Study in Aizawl, Mizoram

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 57172 - 57184

Published: Jan. 1, 2024

Rainfall is vital to all life on Earth, and rainfall prediction essential for various sectors aspects of human society. Hilly areas such as the state Mizoram in India have suffered from landslides during rainy season. This study compares twelve hybrid deep learning machine models predict daily using meteorological variables maximum humidity, minimum temperature, rainfall. The compared include Particle Swarm Optimization (PSO)-Artificial Neural Network (PSO-ANN I), PSO with stacked ANN II), PSO-Bidirectional Long Short-Term Memory (PSO-BiLSTM), PSO-BiLSTM-ANN without Dropout Layer (PSO-BiLSTM-ANN Stacked BiLSTM III), PSO-Long (PSO-LSTM), PSO-LSTM-ANN (PSO-LSTM-ANN LSTM PSO-Recurrent (PSO-RNN-ANN), PSO-Support Vector Regression Linear Kernel (PSO-SVR). We trained tested 12,418 days data 1985 2018 collected by Aizawl Weather Station Mizoram, India. used Mean Absolute Error (MAE), Root Square (RMSE), coefficient determination (R ² ) evaluate performance models. It observed that II model, which a stack BiLSTM, layer, achieved best outperformed PSO-SVR model 6.4%. also requires fewer cells hidden layer than other converges lowest epochs. results show advantage adding RNN, LSTM, models, this provides benchmark predicting area.

Language: Английский

---

Renewable Energy Potential Estimation Using Climatic-Weather-Forecasting Machine Learning Algorithms

Energies, Journal Year: 2023, Volume and Issue: 16(4), P. 1603 - 1603

Published: Feb. 5, 2023

The major challenge facing renewable energy systems in Nigeria is the lack of appropriate, affordable, and available meteorological stations that can accurately provide present future trends weather data solar PV performance. It crucial to find a solution this because information on performance important investors so they assess potential various locations across country. Although Nigerian provides favorable conditions for clean power generation, there little penetration region, since over 95% fossil-fuel-generated. This has been no detailed report showing generation due dysfunctional paper sought fill knowledge gap by providing machine-learning-inspired forecasting environmental parameters be used manufacturing companies evaluating profitability siting region. Crucial such as daily air temperature, relative humidity, atmospheric pressure, wind speed, rainfall were obtained from NASA period 19 years (viz. 2004–2022), resulting collection 6664 high-resolution points. These build diverse regressive neural networks with varying hyperparameters best network arrangement. In summary, low mean-squared error 7 × 10−3 high regression correlations 96% during training.

Language: Английский

---

A comprehensive review towards resilient rainfall forecasting models using artificial intelligence techniques

Green Technologies and Sustainability, Journal Year: 2024, Volume and Issue: 2(3), P. 100104 - 100104

Published: May 27, 2024

Rainfall is one of the remarkable hydrologic variables that directly connected to sustainable environment for any region over globe. The present study aims review different research papers on rainfall forecasting using artificial intelligence (AI) models including a bibliographic assessment most popular AI and comparison results based accuracy parameters. 39 journal papers, published in renowned international journals from 2000 2023, were studied extensively categorize modeling techniques, best models, characteristics input data, period variables, data division, so forth. Although certain drawbacks still exist, reviewed studies suggest may help simulate various geographic locations. In some cases, splitting mechanism was delivered model itself gets improved. recommendations will future researchers fill gaps, especially tuning hyperparameters while building training models. Hybrid advised cases minimize gap between simulated observed data. All aimed achieve resilient era climate change.

Language: Английский

---

Tree-based machine learning and global models for long-term rainfall estimation: intercomparison and evaluation over Bahir Dar, Ethiopia

Journal of Water and Climate Change, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 16, 2025

ABSTRACT This study aims to provide an efficient and accurate model by comparing the tree-based machine learning approach global prediction with European Center for Medium Weather Forecast (ECMWF) predicting long-term rainfall. Light gradient boosting (LGB) regression tree (RT) algorithms are utilized in this compared model. Local metrological parameters such as relative humidity, dew point temperature, minimum maximum wind speed, convective available potential energy, sunshine large-scale climate variable (sea surface temperature) were used input during development. Initially, database was preprocessed then partitioned into a training set testing set. GridsearchCV technique tuning of models. For daily rainfall variation, LGB exhibits strong performance highest coefficient determination (R2 = 0.991; 0.996), lowest root mean squared error (RMSE 1.14 mm; 0.383 mm), (MSE 1.992; 0.146), absolute (MAE 0.899 0.302 mm) monthly time scales. both temporal variations, shows significantly higher accuracy than RT ECMWF. Relative humidity is most influential meteorological parameter identified important random forest (RF) feature value 0.4129. An agricultural decision support system that still development will incorporate suggested models Ethiopia.

Language: Английский

---