The atmospheric boundary layer: a review of current challenges and a new generation of machine learning techniques DOI Creative Commons
Linda Canché-Cab, Liliana San-Pedro, A. Bassam

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(12)

Published: Oct. 17, 2024

Language: Английский

Inferring the relationship between soil temperature and the normalized difference vegetation index with machine learning DOI Creative Commons
Steven Mortier, Amir Hamedpour,

Bart Bussmann

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102730 - 102730

Published: July 20, 2024

Language: Английский

Citations

6
Challenges in data-driven geospatial modeling for environmental research and practice DOI Creative Commons
Diana Koldasbayeva, Polina Tregubova, Mikhail Gasanov

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Dec. 19, 2024

Machine learning-based geospatial applications offer unique opportunities for environmental monitoring due to domains and scales adaptability computational efficiency. However, the specificity of data introduces biases in straightforward implementations. We identify a streamlined pipeline enhance model accuracy, addressing issues like imbalanced data, spatial autocorrelation, prediction errors, nuances generalization uncertainty estimation. examine tools techniques overcoming these obstacles provide insights into future AI developments. A big picture field is completed from advances processing general, including demands industry-related solutions relevant outcomes applied sciences. In this scoping review, authors explore challenges implementing data-driven models—namely machine learning deep algorithms—in research.

Language: Английский

Citations

5
Global soil respiration predictions with associated uncertainties from different spatio-temporal data subsets DOI Creative Commons
Junjie Jiang,

Lingxia Feng,

Junguo Hu

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102777 - 102777

Published: Aug. 23, 2024

Soil respiration (Rs), the second-largest flux in global carbon cycle, is a crucial but uncertain component. To improve understanding of Rs, we constructed single models, and specific models classified by climate type, land cover year data record, elevation range using random forest algorithm to predict Rs values explore associated uncertainty models. The results showed similar overall predictive performance for with an R-squared value greater than 0.63; however, significant differences were observed compared estimate (23 Pg C). All estimated larger model, mainly owing imbalances sample on which prediction based. One exception this result estimates smaller 2020 (95.1 Overall, model closer those obtained temperate zones training distribution, resulted other classification-specific Prediction observations before 2000 tend underestimate Rs. However, use proved helpful addressing persistent temporal spatial sampling. Expanding coverage records both temporally spatially updating database promptly would estimation accuracy while enhancing budget feedback soil regard warming.

Language: Английский

Citations

4
A comparative study of four deep learning algorithms for predicting tree stem radius measured by dendrometer: A case study DOI Creative Commons
Guilherme Cassales, Serajis Salekin, Nick Lim

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103014 - 103014

Published: Jan. 1, 2025

Language: Английский

Citations

0
High precision water quality retrieval in Dianchi Lake using Gaofen 5 data and machine learning methods DOI Creative Commons

Yuewen Feng,

Junqian Zhang, Shaojun Guo

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 25, 2025

Water quality indicators (WQI) reflect both the current state and changing trends of water quality. Extracting these from remote sensing data enables rapid efficient inversion conditions, providing a key step in predicting pollution. The low-precision results WQI limit understanding ecological safety resources. In this paper, Advanced Hyperspectral Imager (AHSI) GF-5 satellite was used to analyze Dianchi Lake. A spectrum processing method based on Savitzky-Golay Standard Normal Variate transformation (SG-SNV) developed, alongside optimal techniques, enhance accuracy predictions for 6 Dianchi, including CODcr, NH3-N, TP, TN, pH, Chl. indicated that (1) For all models, determination coefficients (R2) exceeded 0.85. Back Propagation Nondominated Sorting Genetic Algorithm-II (BP-NGA) model consistently yielded positive most WQI. (2) varied significantly by region season. (3) It recommended build wetlands parks southwest side improve sewage interception pipelines northeast lessen risk eutrophication reducing inflow nitrogen phosphorus.

Language: Английский

Citations

0
Integrating Genetic Algorithm and Geographically Weighted Approaches into Machine Learning Improves Soil pH Prediction in China DOI Creative Commons
Wantao Zhang, Jingyi Ji, Binbin Li

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(6), P. 1086 - 1086

Published: March 20, 2025

Accurate soil pH prediction is critical for management and ecological environmental protection. Machine learning (ML) models have been widely applied in the field of prediction. However, when using these models, spatial heterogeneity relationship between variables often not fully considered, which limits predictive capability especially large-scale regions with complex landscapes. To address challenges, this study collected data from 4335 surface points (0–20 cm) obtained China Soil System Survey, combined a multi-source covariate. This integrates Geographic Weighted Regression (GWR) three ML (Random Forest, Cubist, XGBoost) designs develops geographically weighted machine optimized by Genetic Algorithms to improve values. Compared GWR traditional R2 geographic random forest (GWRF), Cubist (GWCubist), extreme gradient boosting (GWXGBoost) increased 1.98% 14.29%, while RMSE decreased 1.81% 11.98%. Among GWRF model performed best effectively reduced uncertainty mapping. Mean Annual Precipitation Normalized Difference Vegetation Index are two key influencing pH, they significant negative impact on distribution pH. These findings provide scientific basis effective health implementation modeling programs.

Language: Английский

Citations

0
Disentangling Gross Primary Productivity drivers of forested areas in China and its climate zones from 1990 to 2018 DOI Creative Commons
Chenxi Zhu, Guojie Wang, Yuhao Shao

et al.

Journal of Cleaner Production, Journal Year: 2025, Volume and Issue: unknown, P. 145616 - 145616

Published: April 1, 2025

Language: Английский

Citations

0
Predicting unseen chub mackerel densities through spatiotemporal machine learning: Indications of potential hyperdepletion in catch-per-unit-effort due to fishing ground contraction DOI Creative Commons

Shota Kunimatsu,

Hiroyuki Kurota, Soyoka Muko

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 85, P. 102944 - 102944

Published: Dec. 9, 2024

Language: Английский

Citations

3
Spatial autocorrelation in machine learning for modelling soil organic carbon DOI Creative Commons
Alexander Kmoch, Chris Harrison, Jeong-Hwan Choi

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103057 - 103057

Published: Feb. 1, 2025

Language: Английский

Citations

0
A new regular grid-based spatial process on the log-symmetric model for speckled clutter DOI
A. C. B. Machado, Francisco José A. Cysneiros, Abraão D. C. Nascimento

et al.

Spatial Statistics, Journal Year: 2025, Volume and Issue: 67, P. 100900 - 100900

Published: April 25, 2025

Language: Английский

Citations

0