Comparison of hybrid machine learning methods for the prediction of short-term meteorological droughts of Sakarya Meteorological Station in Turkey

Examining optimized machine learning models for accurate multi-month drought forecasting: A representative case study in the USA

The Colorado River has experienced a significant streamflow reduction in recent decades due to climate change, resulting in pronounced hydrological droughts that pose challenges to the environment and human activities. However, current models struggle to accurately capture complex drought patterns, and their accuracy decreases as the lead time increases. Thus, determining the reliability of drought forecasting for specific months ahead presents a challenging task. This study introduces a robust approach that utilizes the Beluga Whale Optimization (BWO) algorithm to train and optimize the parameters of the Regularized Extreme Learning Machine (RELM) and Random Forest (RF) models. The applied models are validated against a KNN benchmark model for forecasting drought from one- to six-month ahead across four hydrological stations distributed over the Colorado River. The achieved results demonstrate that RELM-BWO outperforms RF-BWO and KNN models, achieving the lowest root-mean square error (0.2795), uncertainty (U95 = 0.1077), mean absolute error (0.2104), and highest correlation coefficient (0.9135). Also, the current study uses Global Multi-Criteria Decision Analysis (GMCDA) as an evaluation metric to assess the reliability of the forecasting. The GMCDA results indicate that RELM-BWO provides reliable forecasts up to four months ahead. Overall, the research methodology is valuable for drought assessment and forecasting, enabling advanced early warning systems and effective drought countermeasures.

A hybrid ensemble learning merging approach for enhancing the super drought computation over Lake Victoria Basin

This study introduces a novel Hybrid Ensemble Machine-Learning (HEML) algorithm to merge long-term satellite-based reanalysis precipitation products (SRPPs), enabling the estimation of super drought events in the Lake Victoria Basin (LVB) during the period of 1984 to 2019. This study considers three widely used Machine learning (ML) models, including RF (Random Forest), GBM (Gradient Boosting Machine), and KNN (k-nearest Neighbors), for the emerging HEML approach. The three SRPPs, including CHIRPS (Climate Hazards Group Infra-Red Precipitation with Station), ERA5-Land, and PERSIANN-CDR (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Network-Climate Data Record), were used to merge for developing new precipitation estimates from HEML model. Additionally, classification and regression models were employed as base learners in developing this algorithm. The newly developed HEML datasets were compared with other ML and SRPP products for super-drought monitoring. The Standardized precipitation evapotranspiration index (SPEI) was used to estimate super drought characteristics, including Drought frequency (DF), Drought Duration (DD), and Drought Intensity (DI) from machine learning and SRPPs products in LVB and compared with RG observation. The results revealed that the HEML algorithm shows excellent performance (CC = 0.93) compared to the single ML merging method and SRPPs against observation. Furthermore, the HEML merging product adeptly captures the spatiotemporal patterns of super drought characteristics during both training (1984-2009) and testing (2010-2019) periods. This research offers crucial insights for near-real-time drought monitoring, water resource management, and informed policy decisions.

Evaluation of the sensitivity of meteorological drought in the Mediterranean region to different data record lengths

The division and evaluation of data series used in monitoring drought into different time intervals is a practical approach to detecting the spatial and temporal extent of drought spread. This study aimed to determine meteorological drought's spatial and temporal distribution using overlapping and consecutive periods and cycles of the standardized precipitation index (SPI) time series in the Mediterranean region, Turkey. In the scope of the research, SPI values for the SPI12, SPI6 (1), and SPI6 (2) seasons were calculated for consecutive and overlapping hydrological years (1978-1998/21 years, 1978-2008/31 years, and 1978-2018/41 years) at 28 meteorological stations. Autocorrelation, Mann-Kendall, and Sen slope trend tests were applied at a 5% significance level for each season (SPI12, SPI6 (1), and SPI6 (2)) and different time scales (21, 31, and 41 years). For each season and period, maps of the SPI drought class, average formation of drought class, Mann-Kendall (MK) trend, and Sen's slope (SS) trend test statistics for the Mediterranean region were obtained, and the spatial distribution rate of trends was determined by drawing hypsometric curves. Changes in drought occurrence at different time scales were thoroughly evaluated with the changing length of data recording. Consequently, it was determined that the mild wet (MIW) and mild drought (MID) classes dominate the study area in the Mediterranean region. Significant and nonstationary changes detected in extreme wet and drought occurrences (extreme wet, EW; severe wet, SW; extreme drought, ED; severe drought, SD) were found to pose a risk in the study area. It was observed that there were spatially and temporally insignificant decreasing drought trends in the Mediterranean basin, considering that the time scales of these trends slowed down. Despite a nonsignificant trend from the MID drought class to the MIW drought class, it is predicted that the MIW and MID classes will maintain their dominance in the Mediterranean region. The central part of the study area (central Mediterranean basin) is the region with the highest drought risk.

Assessment of machine learning algorithms and new hybrid multi-criteria analysis for flood hazard and mapping

Floods in Iran cause a lot of damage in different places every year. The 2019 floods of the Gorgan and Atrak rivers basins in the north of Iran were one of the most destructive events in this country. Therefore, investigating the flood hazard of these areas is very necessary to manage probable future floods. For this purpose, in the present study, the capability of Random Forest (RF) and Support Vector Machine (SVM) algorithms was investigated in combination with Sentinel series and Landsat-8 images to prepare the 2019 flood map. Then, the flood hazard map of these areas was prepared using the new hybrid Fuzzy Best Worse Model-Weighted Multi-Criteria Analysis (FBWM-WMCA) model. According to the results of the FBWM-WMCA model, 38.58%, 50.18%, 11.10%, and 0.14% of the Gorgan river basin and 45.11%, 49.96%, 4.17%, and 0.076% of the Atrak river basin are in high, medium, low, and no hazards, respectively. The highest flood hazard areas in Gorgan and Atrak rivers basins in the north, northwest, west, and east, and south and southwest are mostly at medium flood hazard. Also, the results of RF and SVM algorithms with an overall accuracy of more than 85% for Sentinel-1, Sentinel-2, and Landsat-8 images and 80% for Sentinel-3 images indicate that the flooding is related to the western, southwestern, and northern regions including agricultural, bare lands and built up. According to the obtained results and the efficiency of the FBWM-WMCA model, the Gorgan and Atrak rivers basins need proper planning for flood hazard management.

Construction of influencing factor segmentation and intelligent prediction model of college students' cell phone addiction model based on machine learning algorithm

Mobile phone addiction among college students has emerged as a prevalent phenomenon in contemporary society, posing significant challenges to the development and well-being of these individuals. The assessment of the extent of mobile phone addiction has become an urgent concern in the present context. This study employed a sample of 3000 college students from a public university in Zhejiang Province, China, to gather questionnaire data. By utilizing a machine learning algorithm, we identified the most salient factors associated with college students' addiction, with perfectionism emerging as the primary influencer. Additionally, a machine learning-based prediction model for college students' cell phone addiction was developed, yielding a prediction accuracy of 76.68%. This intelligent model can serve as a reliable tool for subsequent evaluations of college students' cell phone addiction.

Short-term forecasting approach of single well production based on multi-intelligent agent hybrid model

The short-term prediction of single well production can provide direct data support for timely guiding the optimization and adjustment of oil well production parameters and studying and judging oil well production conditions. In view of the coupling effect of complex factors on the daily output of a single well, a short-term prediction method based on a multi-agent hybrid model is proposed, and a short-term prediction process of single well output is constructed. First, CEEMDAN method is used to decompose and reconstruct the original data set, and the sliding window method is used to compose the data set with the obtained components. Features of components by decomposition are described as feature vectors based on values of fuzzy entropy and autocorrelation coefficient, through which those components are divided into two groups using cluster algorithm for prediction with two sub models. Optimized online sequential extreme learning machine and the deep learning model based on encoder-decoder structure using self-attention are developed as sub models to predict the grouped data, and the final predicted production comes from the sum of prediction values by sub models. The validity of this method for short-term production prediction of single well daily oil production is verified. The statistical value of data deviation and statistical test methods are introduced as the basis for comparative evaluation, and comparative models are used as the reference model to evaluate the prediction effect of the above multi-agent hybrid model. Results indicated that the proposed hybrid model has performed better with MAE value of 0.0935, 0.0694 and 0.0593 in three cases, respectively. By comparison, the short-term prediction method of single well production based on multi-agent hybrid model has considerably improved the statistical value of prediction deviation of selected oil well data in different periods. Through statistical test, the multi-agent hybrid model is superior to the comparative models. Therefore, the short-term prediction method of single well production based on a multi-agent hybrid model can effectively optimize oilfield production parameters and study and judge oil well production conditions.

Predictive models for short-term load forecasting in the UK's electrical grid

There are global efforts to deploy Electric Vehicles (EVs) because of the role they promise to play in energy transition. These efforts underscore the e-mobility paradigm, representing an interplay between renewable energy resources, smart technologies, and networked transportation. However, there are concerns that these initiatives could burden the electricity grid due to increased demand. Hence, the need for accurate short-term load forecasting is pivotal for the efficient planning, operation, and control of the grid and associated power systems. This study presents robust models for forecasting half-hourly and hourly loads in the UK's power system. The work leverages machine learning techniques such as Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Gaussian Process Regression (GPR) to develop robust prediction models using the net imports dataset from 2010 to 2020. The models were evaluated based on metrics like Root Mean Square Error (RMSE), Mean Absolute Prediction Error (MAPE), Mean Absolute Deviation (MAD), and the Correlation of Determination (R2). For half-hourly forecasts, SVR performed best with an R-value of 99.85%, followed closely by GPR and ANN. But, for hourly forecasts, ANN led with an R-value of 99.71%. The findings affirm the reliability and precision of machine learning methods in short-term load forecasting, particularly highlighting the superior accuracy of the SVR model for half-hourly forecasts and the ANN model for hourly forecasts.

Credit risk assessment of small and micro enterprise based on machine learning

Small and micro enterprises are pivotal in national economic and social development. To foster their growth, managing their credit risks scientifically is crucial. This study starts by examining the credit information of these enterprises. We use imbalanced sample processing algorithms to ensure a balanced representation of minority-class samples. Then, a machine learning classifier is employed to identify key factors contributing to these enterprises' low credibility. Based on these factors, an XGBoost scoring card model is developed. The study reveals: firstly, the integration of the SMOTE algorithm with the XGBoost model exhibits certain performance advantages in handling imbalanced datasets; secondly, trustworthy financial information remains at the heart of crucial risk determinants; thirdly, the XGBoost scoring card model based on significant features effectively enhances the accuracy of credit risk assessment. These insights provide both theoretical references and practical tools for enhancing the robustness of small and micro enterprises, facilitating early warnings on credit risks, and refining financing efficiency.

Analysing spatio-temporal drought characteristics and copula-based return period in Indian Gangetic Basin (1901-2021)

Uncertainty and uneven distribution of monsoonal rainfall and its consequences on crop production is a matter of serious concern in India, specifically, in the Indo-Gangetic plain region. In this study, drought patterns were investigated through standardised precipitation index (SPI) of varying timescales, using the India Meteorological Department (IMD) precipitation data (1901-2021). We analysed the spatio-temporal pattern of different drought characteristics (frequency, duration, severity, intensity) of the Indian Gangetic basin using run theory. The bivariate copula method has been incorporated to combine two drought properties (severity and duration). Copula integrates multivariate distribution and considers the dependency rate among the variables. The five most widely used copulas from various copula families, elliptical (normal, t-copula) and Archimedean (Clayton, Gumbel, Frank), were estimated for modelling, and the best fit copula was selected. The study revealed that seasonal drought is more frequent and intense in the Upper and Middle Gangetic Plain, whereas annual drought is quite scattered in nature. It is worthy to mention that downward drought trends were observed in this agricultural belts significantly after 1965; specifically, in the Upper, Middle, and Trans Gangetic Plain regions. With increasing drought duration and severity, the drought return period raised, but the frequency decreased gradually. Most of the droughts characterised by less duration and severity occurred with a return period below 10 years for the whole region. The major 100 + years return period droughts were to be found after 1960 and their frequencies were significantly higher after 2000. The most recent remarkable droughts with more than 100 years of return occurred during 2008-2011 and 2016-2018 in the Upper and Middle Gangetic plains, whereas in the Lower Gangetic plain, a hundred-year return period drought was occurred during 2010-2013. This study provides agroclimatic-zones-wise significant information of drought characteristics and its nature of occurrence in the Indian Ganga Basin. The results enhance the understanding of drought management and formulation of adaptive strategies to mitigate the adverse impact of droughts.

Sentiment analysis of financial Twitter posts on Twitter with the machine learning classifiers

This paper presents a sentiment analysis combining the lexicon-based and machine learning (ML)-based approaches in Turkish to investigate the public mood for the prediction of stock market behavior in BIST30, Borsa Istanbul. Our main motivation behind this study is to apply sentiment analysis to financial-related tweets in Turkish. We import 17189 tweets posted as "#Borsaistanbul, #Bist, #Bist30, #Bist100″ on Twitter between November 7, 2022, and November 15, 2022, via a MAXQDA 2020, a qualitative data analysis program. For the lexicon-based side, we use a multilingual sentiment offered by the Orange program to label the polarities of the 17189 samples as positive, negative, and neutral labels. Neutral labels are discarded for the machine learning experiments. For the machine learning side, we select 9076 data as positive and negative to implement the classification problem with six different supervised machine learning classifiers conducted in Python 3.6 with the sklearn library. In experiments, 80 % of the selected data is used for the training phase and the rest is used for the testing and validation phase. Results of the experiments show that the Support Vector Machine and Multilayer Perceptron classifier perform better than other classifiers with 0.89 and 0.88 accuracy and AUC values of 0.8729 and 0.8647 respectively. Other classifiers obtain approximately a 78,5 % accuracy rate. It is possible to increase sentiment analysis accuracy with parameter optimization on a larger, cleaner, and more balanced dataset by changing the pre-processing steps. This work can be expanded in the future to develop better sentiment analysis using deep learning approaches.

Multi-temporal SAR Interferometry (MTInSAR)-based study of surface subsidence and its impact on Krishna Godavari (KG) basin in India: a support vector approach

The surface subsidence in the Krishna Godavari (KG) basin in India has increased with the discovery of crude oil and natural gas reserves since 1983. With private players coming up to bag the exploration and refining contracts, there must be timely monitoring of the surface subsidence of the region so that remedial measures for the resettlement of the populations can be taken promptly. Regular monitoring is necessary since the region is fertile and any seawater ingress results in the loss of valuable cultivable land. Multi-temporal SAR Interferometry (MTInSAR) technique has been applied successfully all over the world for the study and regular monitoring of land surface subsidence scenarios. This study utilizes data from Sentinel-1 C-band SAR sensor for MTInSAR-based surface subsidence and RADAR Vegetation Index (RVI)-based vegetation loss for the same season estimation between 2017 and 2022 for the KG basin region. It is inferred from the study that the region has shown surface subsidence of 80 mm/year between April 2020 and June 2022. This study uses support vector regressor (SVR) to predict the loss in forest cover in terms of RVI using MTInSAR-based surface subsidence, VH, and VV backscatter as parameters. It is observed that the SVR gave R2-statistics of 0.89 and 0.873 in the training and testing phases with a mean absolute error (MAE) and root mean squared error (RMSE) of 0.08 and 0.02, respectively. It is also observed that the region showed a loss of 3.21 km2 of cultivable land between 2020 and 2022.

Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, China

Reliable drought prediction plays a significant role in drought management. Applying machine learning models in drought prediction is getting popular in recent years, but applying the stand-alone models to capture the feature information is not sufficient enough, even though the general performance is acceptable. Therefore, the scholars tried the signal decomposition algorithm as a data pre-processing tool, and coupled it with the stand-alone model to build 'decomposition-prediction' model to improve the performance. Considering the limitations of using the single decomposition algorithm, an 'integration-prediction' model construction method is proposed in this study, which deeply combines the results of multiple decomposition algorithms. The model tested three meteorological stations in Guanzhong, Shaanxi Province, China, where the short-term meteorological drought is predicted from 1960 to 2019. The meteorological drought index selects the Standardized Precipitation Index on a 12-month time scale (SPI-12). Compared with stand-alone models and 'decomposition-prediction' models, the 'integration-prediction' models present higher prediction accuracy, smaller prediction error and better stability in the results. This new 'integration-prediction' model provides attractive value for drought risk management in arid regions.

Investigating machine learning models in predicting lake water quality parameters as a 3-year moving average

Lake water quality plays a vital role in the lake ecosystem, including biotic (for living creatures, such as plants, animals, and micro-organisms) and abiotic interactions. In this research, various types of machine learning (ML) methodologies, such as classification and regression tree (CART), chi-squared automatic interaction detector (CHAID), C5 tree, quick, unbiased, and efficient statistical tree (QUEST), along with multilayer perceptron (MLP) neural network, and radial basis function (RBF) neural network, are employed to predict the concentration of water quality parameters (P, EC, TDS, pH, DO, NH3, SO4, and θ). Lake Erie is situated at the international border of the USA and Canada. The C5 tree and QUEST tree are used to classify data and predict the number of groups, while the other methods are used to predict the concentration of water quality parameters in the form of a 3-year moving average. The greater matching between the observed and predicted data of dissolved oxygen (NSE = 0.978, bias = 0.126) shows that the CART decision tree has higher accuracy in correctly detecting the concentration of this parameter. The C5 tree could identify 33 groups correctly out of 36 total groups, which shows better accuracy for the C5 tree in classifying the data for this parameter.

Prediction of suspended sediment concentration in the lower Yellow River in China based on the coupled CEEMD-NAR model

The scientific and accurate prediction of suspended sediment concentrations is of great importance for river management in the lower reaches of the Yellow River and for the scheduling of water conservancy projects in the upper and middle reaches. In order to solve the influence of the non-linear and non-smooth characteristics of the suspended sediment concentration series in the lower Yellow River on the prediction results and improve the prediction accuracy, this paper proposes a coupled model based on Complementary Ensemble Empirical Mode Decomposition (CEEMD) and non-linear autoregressive (NAR) model. Take the predicted suspended sediment concentrations in the lower reaches of the Yellow River at the Huayuankou hydrographic station as an example. The accuracy and stability of the coupled CEEMD-NAR model were verified through the Gaocun and Lijin hydrological stations. The CEEMD-NAR model predicted suspended sediment concentrations with a Nash-Sutcliffe efficiency (NSE) factor of 0.93. The three statistical evaluation indicators of the CEEMD-NAR model, mean absolute error (MAE), mean relative error (MRE), and root mean square error (RMSE) were 2.12 kg/m³, 1.07, and 3.75 kg/m³ respectively. In contrast to the NAR, EMD-NAR, and EEMD-NAR models, the coupled CEEMD-NAR model has good stability and high prediction accuracy and can be used in non-linear, non-smooth suspended sediment concentration long series prediction.

Influence of the impoundment of the Three Gorges Reservoir on hydrothermal conditions for fish habitat in the Yangtze River

The thermal regimes of rivers play an important role in the overall health of aquatic ecosystems. Modifications to water temperature regimes resulting from dams and reservoirs have important consequences for river ecosystems. This study investigates the impacts of the impoundment of the Three Gorges Reservoir (TGR) on the water temperature regime of fish spawning habitats in the middle reach of the Yangtze River, China. Mike 11 model is used to analyze the temporal and spatial variation of water temperatures of the expanse of 400 km along the river, from Yichang to Chenglingji. The water temperature alterations caused by the operation of the TGR are assessed with river temperature metrics. The impact on spawning habitats due to water temperature variation was also discussed in different impoundments of the TGR. The results show that the TGR has significantly altered the downstream water temperature regime, affecting the baseline deviation and phase shift of the water temperature. Such impacts on the thermal regime of the river varied with the impoundment level. The effects of the TGR on the water temperature regime decreased as the distance from the structure to the sample site increased. The water temperature regime alterations have led to the delay of the spawning times of the four famous major carp (FFMC) species. The results could be used to identify the magnitudes of water temperature alterations induced by reservoirs in the Yangtze River and provide useful information to design ecological operations for the protection of river ecosystem integrity in regulated rivers.

Pre- and post-dam river water temperature alteration prediction using advanced machine learning models

Dams significantly impact river hydrology by changing the timing, size, and frequency of low and high flows, resulting in a hydrologic regime that differs significantly from the natural flow regime before the impoundment. For precise planning and judicious use of available water resources for agricultural operations and aquatic habitats, it is critical to assess the dam water's temperature accurately. The building of dams, particularly several dams in rivers, can significantly impact downstream water. In this study, we predict the daily water temperature of the Yangtze River at Cuntan. Thus, this work reveals the potential of machine learning models, namely, M5 Pruned (M5P), Random Forest (RF), Random Subspace (RSS), and Reduced Error Pruning Tree (REPTree). The best and effective input variables combinations were determined based on the correlation coefficient. The outputs of the various machine learning algorithm models were compared with recorded daily water temperature data using goodness-of-fit criteria and graphical analysis to arrive at a final comparison. Based on a number of criteria, numerical comparison between the models revealed that M5P model performed superior (R2 = 0.9920, 0.9708; PCC = 0.9960, 0.9853; MAE = 0.2387, 0.4285; RMSE = 0.3449, 0.4285; RAE = 6.2573, 11.5439; RRSE = 8.0288, 13.8282) in pre-impact and post-impact spam, respectively. These findings suggest that a huge wave of dam construction in the previous century altered the hydrologic regimes of large and minor rivers. This study will be helpful for the ecologists and river experts in planning new reservoirs to maintain the flows and minimize the water temperature concerning spillway operation. Finally, our findings revealed that these algorithms could reliably estimate water temperature using a day lag time input in water level. They are cost-effective techniques for forecasting purposes.