Machine Learning-Based Forecasting of Waste Generation Proxies Under Data-Limited Conditions for Supporting Adaptive and Sustainable Citarum River Management

Recent developments in machine learning and deep learning have led to the use of multiple algorithms to make better predictions. Surgical units in hospitals allocate their resources for day surgeries based on the number of elective patients, which is mostly disrupted by emergency surgeries. Sixteen different models were constructed for this comparative study, including four simple and twelve hybrid models for predicting the demand for endocrinology, gastroenterology, vascular, urology, and pediatric surgical units. The four simple models used were seasonal autoregressive integrated moving average (SARIMA), support vector regression (SVR), multilayer perceptron (MLP), and long short-term memory (LSTM). The twelve hybrid models used were a combination of any two of the above-mentioned simple models, namely, SARIMA–SVR, SVR–SARIMA, SARIMA–MLP, MLP–SARIMA, SARIMA–LSTM, LSTM–SARIMA, SVR–MLP, MLP–SVR, SVR–LSTM, LSTM–SVR, MLP–LSTM, and LSTM–MLP. Data from the period 2012–2018 were used to build and test the models for each surgical unit. The results indicated that, in some cases, the simple LSTM model outperformed the others while, in other cases, there was a need for hybrid models. This shows that surgical units are unique in nature and need separate models for predicting their corresponding surgical volumes.

Accurately forecasting load profiles, especially peak catching, is a challenge due to the stochastic nature of consumption. In this paper, we applied the following three models for forecasting: Long Short-Term Memory (LSTM); Support Vector Regression (SVR); and the combined model, which is a blend of SVR, Gated Recurrent Units (GRU), and Linear Regression (LR) to forecast 24 h-ahead load profiles. Household (HH), heat pump (HP), and electric vehicle (EV) loads are singular, and these were collectively considered with one-year load profiles. This study tackles the issue of accurately forecasting load profiles by evaluating LSTM, SVR, and an ensemble model for predicting energy consumption in HH, HP, and EV loads. A novel forecast correction mechanism is introduced, adjusting forecasts every eight hours to increase reliability. The findings highlight the potential of deep learning in enhancing energy demand forecasting, especially in identifying peak loads, which contributes to more stable and efficient grid operations. Visual and validation data were investigated, along with the models’ performances at different levels, such as off-peak, on-peak, and entirely. Among all models, LSTM performed slightly better in most of the factors, particularly in peak capturing. However, the blended model showed slightly better performance than LSTM for EV power load forecasting, with an on-peak mean absolute percentage error (MAPE) of 21.45%, compared to 29.24% and 22.02% for SVR and LSTM, respectively. Nevertheless, visual analysis clearly showed the strong ability of LSTM to capture peaks. This LSTM potential was also shown by the mean absolute percentage error (MAPE) and symmetric mean absolute percentage error (SMAPE) during the on-peak period, with around 3–5% improvement compared to SVR and the blended model. Finally, LSTM was employed in predicting day-ahead load profiles using measured data from four grids and showed high potential in capturing peaks with MAPE values less than 10% for most of the grids.

Highlights A 10-year dataset of time-series MODIS imagery and in situ Chl- a concentration were curated for Lake Okeechobee. LSTM significantly outperformed KNN, SVR, and RF for Chl- a prediction and subsequent HAB detection. The optimal window length was found to be 13 days with a 4-day temporal resolution for the LSTM model. KNN, SVR, and RF models were not effective at utilizing the temporal dynamics of the input features. Abstract. Harmful algal blooms (HABs) in inland waterbodies are a global concern due to their negative impact on human, animal, and ecosystem health. Chlorophyll-a (Chl-a) concentration is an important water quality parameter for monitoring HABs. While statistical and machine learning (ML) models have been widely studied to predict Chl-a concentration and HABs based on single-time-point satellite data, this work assessed whether long short-term memory (LSTM) can improve both tasks by leveraging temporal features in time-series MODIS satellite images compared to three classical ML models, including k-nearest neighbor (KNN), support vector regression (SVR), and random forest (RF). A dataset of daily MODIS images and monthly in situ Chl-a concentration measurements from 2011 to 2020 was curated for Lake Okeechobee, Florida. A window size of 13 days with a temporal resolution of four days was found to produce the optimal performance for LSTM, which significantly outperformed KNN, SVR, and RF for Chl-a prediction with a root mean square error of 11.95 µg/L, a mean absolute error of 8.55 µg/L, and a R 2 value of 0.43. The superior performance of LSTM for Chl-a prediction was likely due to its ability to leverage the temporal dynamics in the features associated with HAB development. The Chl-a predictions were further used to determine HAB events, showing better accuracy and a significantly higher F1 score for LSTM over the other models. The study suggested that combining LSTM with high-temporal-resolution time-series data should be preferred over applying common ML models on time-series or single-time-point remote sensing data for Chl-a and HAB monitoring. Keywords: Cyanobacteria, LSTM, Machine Learning, Remote Sensing, Water Quality.

To alleviate traffic congestion and support the development of real-time traffic and public transport, this paper conducts research on adopting support vector regression (SVR) and long short term memory (LSTM) to predict traffic flow of the lane, and then compares the results with that using the quadratic exponential smoothing. The consequence shows that SVR and LSTM have better prediction accuracy, about 1%–3% in terms of MAPE, than quadratic exponential smoothing, and SVR is slightly better than LSTM. Furthermore, in order to improve the predictive accuracy of model, we compare the performance of grid search, whale optimization algorithm (WOA) and genetic algorithm (GA) respectively in the respect of optimizing models’ parameters. The optimization effect of WOA-SVR and WOA-LSTM is better than the other two models respectively, about 0.9% and 2.52% better than GA-SVR and GA-LSTM while 0.29% and 2.32% better than GridSearch-SVR and GridSearch-LSTM considering MAPE.KeywordsShort-term traffic flow predictionSupport vector regressionLong short term memoryWhale optimization algorithmGenetic algorithm

LSTM and Statistical Learning for Dynamic Inferential Modeling with Applications to a 660MW Boiler

Predicting the geopolymerization process of fly ash-based geopolymer using deep long short-term memory and machine learning

Displacement predictions are essential to landslide early warning systems establishment. Most existing prediction methods are focused on finding an individual model that provides a better result. However, the limitation of generalization that is inherent in all models makes it difficult for an individual model to predict different cases accurately. In this study, a novel coupled method was proposed, combining the long short-term memory (LSTM) neural networks and support vector regression (SVR) algorithm with optimal weight. The Shengjibao landslide in the Three Gorges Reservoir area was taken as a case study. At first, the moving average method was used to decompose the cumulative displacement into two components: trend and periodic terms. Single-factor models based on LSTM neural networks and SVR algorithms were used to predict the trend terms of displacement, respectively. Multi-factors LSTM and SVR models were used to predict the periodic terms of displacement. Precipitation, reservoir water level, and previous displacement are considered as the candidate factors for inputs in the models. Additionally, ensemble models based on the SVR algorithm are used to predict the optimal weight to combine the results of the LSTM and SVR models. The results show that the LSTM models display better performance than SVR models; the ensemble model with optimal weight outperforms other models. The prediction accuracy can be further improved by also considering results from multiple models.

Crude oil or petroleum is a non-renewable energy source derived from organic materials whose formation process is lengthy. Crude oil is a commodity whose prices often fluctuate. When there is a fluctuation, a nation's economy will be affected. The crude oil price datasets are categorized as non-linear. This research used two models to compare the performance of those two models to find the best model to predict Brent crude oil prices. The models used in this research are Long Short-Term Memory (LSTM) and Support Vector Regression (SVR). Those two methods are widely used for a similar case, such as forecasting the stock price. The dataset used in this study is the price of Brent crude oil from May 1987 to May 2022. The result of this study indicates that the deep learning algorithm, LSTM, performs better in forecasting the price of Brent crude oil with a root mean squared error value of 1.543. Index Terms”Crude Oil, Long Short-Term Memory (LSTM), Support Vector Regression (SVR), Deep Learning, Forecasting.

Efficient and sustainable transportation is crucial for addressing the environmental and social challenges associated with urban mobility. Accurate estimation of travel time plays a pivotal role in traffic management and trip planning. This study focused on leveraging machine learning models to enhance travel time estimation accuracy on toll roads under diverse traffic conditions. Two models were developed for travel time estimation under a variety of traffic conditions on the Don Muang Tollway, Bangkok, Thailand: a long short-term memory (LSTM) recurrent neural network model and a support vector regression (SVR) model. Missing data were treated using the proposed segment-based data imputation method. Unlike other studies, the effects of missing input data on the travel time model performance were also analyzed. Traffic parameters, such as speed and flow, along with other relevant parameters (time of day, day of the week, holiday indicators, and a missing data indicator), were fed into each model to estimate travel time on each of the four specific routes. The LSTM and SVR results had similar performance levels based on evaluating the all-day pooled data. However, the mean absolute percentage errors were lower for LSTM during peak periods, while SVR performed slightly better during off-peak periods. Additionally, LSTM coped substantially better than SVR with unusual traffic fluctuations. The sensitivity analysis of the missing input data in this study also revealed that the LSTM model was more robust to the high degree of missing data than the SVR model.

Accurate forecasting of solar power generation is crucial for island countries like Sri Lanka, particularly when large-scale solar farms are integrated into the power grid. Significant variations in solar power, resulting from the intermittent nature of solar irradiance, impact the reliability and stability of the power grid. This work reports a novel approach for predicting short-term solar power generation using ensemble models. Historical solar power generation data were acquired from the Buruthakanda solar park in Hambantota, Sri Lanka. Different weather parameter-based machine learning algorithms, such as Artificial Neural Network (ANN), Random Forest Regression, Support Vector Regression, and time series regression models such as Long Short Term Memory (LSTM), 1-Dimensional Convolutional Neural Network (1D-CNN), and LSTM-CNN, are utilized for forecasting solar power generation. The ANN and LSTM predictions had the lowest Root Mean Square Error (RMSE) values, 0.0429 and 0.0489, respectively. Several ensemble models were developed using ANN and LSTM algorithms, and it was found that the (ANN+LSTM)+(Extreme Gradient Boosting) ensemble has the lowest RMSE of 0.04, which is 7.25% and 22.25% lower than single ANN and LSTM models. The R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of the ensemble model is approximately 0.975, demonstrating the reliability of the model. Additionally, the impact of Numerical Weather Prediction (NWP) errors on the accuracy of machine learning algorithms is investigated. The RMSE increases by nearly 17.5% when NWP errors are incorporated into the ensemble models.

A multivariate ultra-short-term wind speed forecasting model by employing multistage signal decomposition approaches and a deep learning network

Accurate crop yield prediction is critical for informed agricultural planning, food distribution, and policy formulation. Traditional statistical models often fail to capture the nonlinear and temporal dynamics inherent in crop yield data. This Study introduces a novel hybrid Separate Evaluation of Regression models with Weighted Integration (SERWI) ensemble model, a novel hybrid ensemble model that integrates three machine learning algorithms: Long Short-Term Memory (LSTM) networks, Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost). These base learners combine using a dynamic inverse RMSE-based weighting strategy that adaptively assigns higher weights to models exhibiting superior validation performance. The model is trained and evaluated using a comprehensive multi-decadal dataset sourced from the Season and Crop Report 2023-24 published by the Government of Tamil Nadu, which includes historical data on cultivated area, production, and yield of principal food grains, specifically focusing on foodgrains crop. Additionally, a detailed comparative analysis is performed against several individual models and ensemble combinations, including LSTM, SVR, XGBoost, Random Forest Regressor (RFR), Gaussian Process, and hybrid pairs such as LSTM plus SVR, SVR plus XGBoost, and LSTM plus RFR. SERWI outperformed the evaluated baseline models, achieving an RMSE of 70.16, MSE of 4923.07, MAE of 47.93, and R² of 0.9918 on the test set. These results indicate strong predictive performance and potential scalability for practical agricultural yield forecasting.

Forecasting gold prices is always a crucial topic in fintech. This article presents a new time series forecasting model for predicting London gold market prices. The model incorporates fully integrated empirical mode decomposition with adaptive noise (CEEMDAN), support vector regression (SVR), and long short-term memory (LSTM) neural networks. The proposed model utilizes the CEEMDAN and significance judgment method of t test method to decompose the golden time series data into intrinsic mode functions (IMFs) across three different frequency bands. Subsequently, SVR and LSTM are employed to fit and evaluate the IMFs. SVR is effective in predicting high-frequency and low-frequency components, while LSTM is proficient in capturing the trend component of time series. The hybrid method exhibited exceptional prediction performance, with a mean square error (MSE) of 111.23. Many ablation experiments are conducted to verify the effectiveness of LSTM and SVR in all base models, and to confirm the positive role of frequency decomposition in improving predictions.

Aviation emissions originated from the fuel burn have been hot topics by engineers and policy-makers due to their harmful effects on the environment and thereby human health as well as sustainability. In this study, it is tried that several emission indexes (EIs) involving CO, HC and NOx as well as fuel flow of several commercial aircraft engines (CAEs) are predicted using support vector regression (SVR) and long short-term memory (LSTM) approaches for take-off phase. Moreover, exergo-environmental parameters involving exergy efficiency (ExEFF), wasted exergy ratio (WExR) and environmental effect factor (EEF) pertinent to CAEs are computed employing thermodynamics laws. While establishing the models, rated thrust, by-pass ratio, overall pressure ratio and combustion type of the CAEs are utilized as the model inputs. According to the findings of emission modelling, the coefficient of determination (R2) of EI NOx and EI CO of the CAEs is found as 0.929074 and 0.960277 with SVR, whereas their R2 values are elevated to 0.954878 and 0.989283 with LSTM approach, respectively. However, R2 of EI HC is determined lower with 0.632280 (by SVR) and 0.651749 (by LSTM). On the other hand, exergo-environmental parameters for the CAEs are estimated with high correctness at both models. Namely, R2 of ExEFF and EEF regarding the CAEs are computed as 0.991748 and 0.989067 by SVR; however, these are calculated as 0.994785 and 0.992797 by LSTM method. To model these parameters with low error by using significant design variables as model inputs could help in predicting emission and environmental metrics for new engine designs.

Early warning systems depend heavily on the accuracy of landslide displacement forecasts. This study focuses on the Bazimen landslide located in the Three Gorges Reservoir region and proposes a hybrid prediction approach combining support vector regression (SVR) and long short-term memory (LSTM) networks. These models are optimized via the K-Nearest Neighbor (KNN) algorithm. Initially, cumulative displacement data were separated into trend and cyclic elements using a smoothing approach. SVR and LSTM were then used to predict the components, and KNN was introduced to optimize input factors and classify the results, improving accuracy. The final KNN-optimized SVR-LSTM model effectively integrates static and dynamic features, addressing limitations of traditional models. The results show that LSTM performs better than SVR, with an RMSE and MAPE of 24.73 mm and 1.87% at monitoring point ZG111, compared to 30.71 mm and 2.15% for SVR. The sequential hybrid model based on KNN-optimized SVR and LSTM achieved the best performance, with an RMSE and MAPE of 23.11 mm and 1.68%, respectively. This integrated model, which combines multiple algorithms, offers improved prediction of landslide displacement and practical value for disaster forecasting in the Three Gorges area.