Remote sensing and integration of machine learning algorithms for above-ground biomass estimation in Larix principis-rupprechtii Mayr plantations: a case study using Sentinel-2 and Landsat-9 data in northern China DOI Creative Commons

Jamshid Ali,

Haoran Wang, Kaleem Mehmood

et al.

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 13

Published: April 2, 2025

Estimating above-ground biomass (AGB) is important for ecological assessment, carbon stock evaluation, and forest management. This research assesses the performance of machine learning algorithms XGBoost, SVM, RF using data from Sentinel-2 Landsat-9 satellites. The study influence significant spectral bands vegetation indices on accuracy AGB estimate. results presented in paper indicate that were more effective than data. mainly because it had higher spatial resolution, which enabled model gradients structural attributes accurately. XGBoost performed best with an R 2 0.82 RMSE 0.73 Mg/ha 0.80 0.71 Landsat-9. In current study, SVM also showed a substantial 0.79 0.76 For Sentinel-2, random achieved 0.74 0.93 Mg/ha, Landsat 9 yielded 0.72 0.88 Mg/ha. Thus, variable importance analysis, have predicting AGB. As expected their application research, these predictors consistently emerged as highly across models datasets. demonstrates potential integrating remote sensing to achieve accurate efficient assessment.

Language: Английский

Hypertuned wavelet convolutional neural network with long short-term memory for time series forecasting in hydroelectric power plants DOI
Stéfano Frizzo Stefenon, Laio Oriel Seman, Evandro Cardozo da Silva

et al.

Energy, Journal Year: 2024, Volume and Issue: unknown, P. 133918 - 133918

Published: Nov. 1, 2024

Language: Английский

Citations

4
Modeling soil respiration in summer maize cropland based on hyperspectral imagery and machine learning DOI Creative Commons

Fanchao Zeng,

Jinwei Sun,

Huihui Zhang

et al.

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 7, 2025

Introduction Soil respiration (SR), the release of carbon dioxide (CO 2 ) from soil due to decomposition organic matter and root respiration, is an important indicator for understanding agricultural cycling assessing anthropogenic impacts on environment. Hyperspectral remote sensing offers a potential rapid, non-destructive approach monitoring in agriculture. However, it remains uncertain whether hyperspectral can provide accurate efficient method estimating SR rate croplands, particularly across different maize growth stages under varying drought conditions. Methods In study, we investigated combining data with machine learning model (ML) quantify croplands. A field experiment was conducted, imagery were collected during four stages: Jointing Stage (JS), Tasseling (TS), Flowering (FS), Grain Filling (GFS). We compared performance traditional multiple linear regression (MLR) that ML (extreme gradient boosting, XGBoost), simulating these stages. Results Our findings demonstrated simulation XGBoost model, utilizing temperature ( Ts data, outperformed MLR model. Across stages, simulated by R = 0.8103) more reliable than 0.7451). The also effectively capture impact treatments SR. Discussion model’s tree-based structure allows complex interactions nonlinear patterns within variables, while its high sensitivity changes rates conditions makes modeling linear-based This study highlights great promise combined imaging predicting which will help guide future management environmental informatics.

Language: Английский

Citations

0
Capturing complex electricity load patterns: A hybrid deep learning approach with proposed external-convolution attention DOI Creative Commons
Mohammad Sadegh Zare, Mohammad Reza Nikoo, Mingjie Chen

et al.

Energy Strategy Reviews, Journal Year: 2025, Volume and Issue: 57, P. 101638 - 101638

Published: Jan. 1, 2025

Language: Английский

Citations

0
Machine Learning for Price Prediction and Risk-Adjusted Portfolio Optimization in Cryptocurrencies DOI

Dailin Song

Advances in finance, accounting, and economics book series, Journal Year: 2025, Volume and Issue: unknown, P. 321 - 356

Published: Jan. 22, 2025

Accurately forecasting price swings is nowadays essential to investors looking maximize their portfolios as the cryptocurrency markets continue develop and fluctuate rapidly. The intricate, non-linear patterns in these are sometimes difficult for traditional financial models depict. In response, this paper presents two machine learning techniques predicting bitcoin prices: Extreme Gradient Boosting Long Short-Term Memory. study first evaluates how well forecast Bitcoin prices, assessing accuracy with measures like Mean Absolute Error Root Squared Error. Four significant cryptocurrencies then predicted by LSTM. order allocate assets a way that optimizes returns while reducing risk, forecasted prices incorporated into portfolio optimization algorithms utilizing Monte Carlo simulation efficient frontier. results of show approaches may be used improve investing strategies through optimal allocation, addition projecting values.

Language: Английский

Citations

0
A weather station selection method based on the simulated annealing algorithm for electric load forecasting DOI

Narjes Salmabadi,

Majid Salari, Alireza Shadman

et al.

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 23, 2025

Language: Английский

Citations

0
Integrated finite element analysis and machine learning approach for exploring the flexural behavior of steel-spontaneous combustion coal gangue aggregate concrete composite beams with studs DOI
Tirui Zhang, Qinghe Wang, Xinlong Zhang

et al.

Structures, Journal Year: 2025, Volume and Issue: 72, P. 108265 - 108265

Published: Jan. 24, 2025

Language: Английский

Citations

0
NOx Concentration Modeling in CFB Coal-Fired Power Plants Based on Feature Engineering and Deep Random Forest DOI
Gaocheng Yan,

Jie Qiao,

Yuchao Wu

et al.

Process Safety and Environmental Protection, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Time Series Foundation Model for Improved Transformer Load Forecasting and Overload Detection DOI Creative Commons

Yikai Hou,

Chao Ma, Xiang Li

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(3), P. 660 - 660

Published: Jan. 31, 2025

Simple load forecasting and overload prediction models, such as LSTM XGBoost, are unable to handle the increasing amount of data in power systems. Recently, various foundation models (FMs) for time series analysis have been proposed, which can be scaled up large variables datasets across domains. However, simple pre-training setting makes FMs unsuitable complex downstream tasks. Effectively handling real-world tasks depends on additional data, i.e., covariates, prior knowledge. Incorporating these through structural modifications is not feasible, it would disrupt pre-trained weights. To address this issue, paper proposes a frequency domain mixer, FreqMixer, framework enhancing task-specific analytical capabilities FMs. FreqMixer an auxiliary network backbone that takes covariates input. It has same number layers communicates with at each layer, allowing incorporation knowledge without altering backbone’s structure. Through experiments, demonstrates high efficiency performance, reducing MAPE by 23.65%, recall 87%, precision 72% transformer during Spring Festival while improving 192.09% accuracy 14% corresponding prediction, all processing from over 160 transformers just 1M parameters.

Language: Английский

Citations

0
Insights into the high-temperature oxidation and electrochemical corrosion behavior of Si alloyed TiAl alloys and the prediction of corrosion behavior using machine learning approaches DOI
Y. Garip,

O. Ozdemir

Journal of Alloys and Compounds, Journal Year: 2025, Volume and Issue: unknown, P. 179023 - 179023

Published: Feb. 1, 2025

Language: Английский

Citations

0
An Interpretable XGBoost-SHAP Machine Learning Model for Reliable Prediction of Mechanical Properties in Waste Foundry Sand-Based Eco-Friendly Concrete DOI Creative Commons
Meysam Alizamir, Mo Wang, Rana Muhammad Adnan Ikram

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104307 - 104307

Published: Feb. 1, 2025

Language: Английский

Citations

0