A GLMER-based pedotransfer function expressing the relationship between total organic carbon and bulk density in forest soils DOI Creative Commons
Václav Zouhar, Aleš Kučera, Karel Drápela

et al.

Journal of Forest Science, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 17, 2024

Owing to its role in mitigating CO2 the atmosphere, total organic carbon (TOC) stock of soil, a key component terrestrial cycle, is significant interest as regards climate change. To determine TOC stock, it first necessary soil's bulk density (BD), determined through intact soil sampling; however, forest soils, can be difficult BD soils with high levels stoniness and/or tree root coverage. Furthermore, method time-consuming and labour-intensive, making impractical for studies over large areas. In such cases, using pedotransfer function (PTF) expressing relationship between BD. The aim this study was PTF actual data obtained from 777 pits dug part Czech Republic's National Forest Inventory (NFI). Within NFI, assessed undisturbed core samples, while mixed samples same genetic horizons. Both generalised linear (GLM) mixed-effects (GLMER) models were used, final GLMER model best individual natural areas within NFI dataset. GLMER-based described widely applied accurately estimate via concentration at temperate sites where cover previously made technically impossible take standard methods.

Language: Английский

Harnessing Artificial Intelligence, Machine Learning and Deep Learning for Sustainable Forestry Management and Conservation: Transformative Potential and Future Perspectives DOI Creative Commons

T. J. Wang,

Yiping Zuo,

Teja Manda

et al.

Plants, Journal Year: 2025, Volume and Issue: 14(7), P. 998 - 998

Published: March 22, 2025

Plants serve as the basis for ecosystems and provide a wide range of essential ecological, environmental, economic benefits. However, forest plants other systems are constantly threatened by degradation extinction, mainly due to misuse exhaustion. Therefore, sustainable management (SFM) is paramount, especially in wake global climate change challenges. SFM ensures continued provision forests both present future generations. In practice, faces challenges balancing use conservation forests. This review discusses transformative potential artificial intelligence (AI), machine learning, deep learning (DL) technologies management. It summarizes current research technological improvements implemented using AI, discussing their applications, such predictive analytics modeling techniques that enable accurate forecasting dynamics carbon sequestration, species distribution, ecosystem conditions. Additionally, it explores how AI-powered decision support facilitate adaptive strategies integrating real-time data form images or videos. The manuscript also highlights limitations incurred ML, DL combating management, providing acceptable solutions these problems. concludes perspectives immense modernizing SFM. Nonetheless, great deal has already shed much light on this topic, bridges knowledge gap.

Language: Английский

Citations

1
Mapping sub-surface distribution of soil organic carbon stocks in South Africa's arid and semi-arid landscapes: Implications for land management and climate change mitigation DOI Creative Commons
Omosalewa Odebiri, Onisimo Mutanga, John Odindi

et al.

Geoderma Regional, Journal Year: 2024, Volume and Issue: 37, P. e00817 - e00817

Published: May 23, 2024

Soil organic carbon (SOC) stocks are critical for land management strategies and climate change mitigation. However, understanding SOC distribution in South Africa's arid semi-arid regions remains a challenge due to data limitations, the complex spatial sub-surface variability driven by desertification degradation. Thus, support soil land-use practices as well advance mitigation efforts, there is an urgent need provide more precise stock estimates within regions. Hence, this study adopted remote-sensing approaches determine of influence environmental co-variates at four depths (i.e., 0-30 cm, 30-60 60-100 100-200 cm). Using two regression-based algorithms, i.e., Extreme Gradient Boosting (XGBoost) Random Forest (RF), found former (RMSE values ranging from 7.12 t/ha 29.55 t/ha) be superior predictor comparison latter 7.36 31.10 t/ha). Nonetheless, both models achieved satisfactory accuracy (R

Language: Английский

Citations

5
Assessing the potential of multi-source remote sensing data for cropland soil organic matter mapping in hilly and mountainous areas DOI
Peng Li, Xiaobo Wu,

C Feng

et al.

CATENA, Journal Year: 2024, Volume and Issue: 245, P. 108312 - 108312

Published: Aug. 12, 2024

Language: Английский

Citations

5
Assessment of multivariate associations and spatial variability of forest soil properties and their stand factors in the Czech Republic DOI Creative Commons
Vincent Yaw Oppong Sarkodie, Radim Vašát, Karel Němeček

et al.

Soil and Water Research, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 3, 2025

Knowing the relationship between forest soil properties and their stand conditions is relevant for sustainable exploitation management of soils. This study examines influence environmental factors on within environments. We further assessed spatial variability these controlling factors. A harmonised database entire areas Czech Republic was considered; however, only 851 sampling points with complete data used out more than 8 thousand in database. The topsoil mineral layer 0–30 cm analysed. Principal component analysis to determine relationships nugget ratios semivariograms cross-variograms were evaluate dependence properties, Forest types reaction availability cations topsoils. Phosphorus influenced by aluminium cation exchange capacity. There are higher concentrations total phosphorus under broadleaved forest.

Language: Английский

Citations

0
Soil Organic Carbon (SOC) Prediction using Super Learner Algorithm Based on the Remote Sensing Variables DOI Creative Commons
Y. Jo, Palash Panja, Hanseup Kim

et al.

Environmental Challenges, Journal Year: 2025, Volume and Issue: unknown, P. 101160 - 101160

Published: April 1, 2025

Language: Английский

Citations

0
High-performance prediction of soil organic carbon using automatic hyperparameter optimization method in the yellow river delta of China DOI
Yingqiang Song,

Feng Wang,

Weihao Yang

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 236, P. 110490 - 110490

Published: May 8, 2025

Language: Английский

Citations

0
Current limitations and future research needs for predicting soil precompression stress: A synthesis of available data DOI Creative Commons
Lorena Chagas Torres, Attila Nemes, Loraine ten Damme

et al.

Soil and Tillage Research, Journal Year: 2024, Volume and Issue: 244, P. 106225 - 106225

Published: Aug. 2, 2024

Precompression stress, compression index, and swelling index are used for characterizing the compressive behavior of soils, essential soil properties establishing decision support tools to reduce risk compaction. Because measurements time-consuming, often derived through pedotransfer functions. This study aimed develop a comprehensive database with additional information on basic properties, site characteristics, methodological aspects sourced from peer-reviewed literature, random forest models predicting precompression stress using various subsets database. Our analysis illustrates that data primarily originate limited number countries. There is predominance data, while little or recompression available. Most were topsoils conventionally tilled arable fields, which not compatible knowledge subsoil compaction serious problem. The compilation unveiled considerable variations in test procedures methods calculating across different studies, concentration at moisture conditions above field capacity. exhibited unsatisfactory predictive performance although they performed better than previously developed models. Models showed slight improvement power when underlying restricted specific calculation method. Although our offers broader coverage previous lack standardization complicates development based combined datasets. Methodological and/or functions translate results between methodologies needed ensure consistency enable comparison, robust predictions. Moreover, wider range characterize mechanical as function moisture, similar hydraulic functions, predict parameters such

Language: Английский

Citations

2
Spatial Distribution of Forest Soil Base Elements (Ca, Mg and K): A Regression Kriging Prediction for Czechia DOI Open Access
Vincent Yaw Oppong Sarkodie, Radim Vašát, Karel Němeček

et al.

Forests, Journal Year: 2024, Volume and Issue: 15(7), P. 1123 - 1123

Published: June 28, 2024

Base cations have declined within European forests due to leaching, accelerated by atmospheric acid deposition. This study aims at predicting the spatial distribution of pseudototal content Ca, Mg, and K for coniferous, broadleaved mixed forest stands. A harmonised database about 7000 samples from top mineral layer 0–30 cm entire areas Czech Republic was used. regression kriging model used prediction elements. The influence covariates assessed using generalized additive models location scale shape (GAMLSS). variance explained best Ca with R2 0.32, Mg 0.30, 0.26. Model fitting ratio performance inter-quartile distance (RPIQ) showed as fit a value 1.12, followed 0.87, 0.25. exhibited GAMLSS, compared based on their AIC matrix values. predicted in this provides information policy will provide sustainable management forests.

Language: Английский

Citations

1
An integrated feature selection approach to high water stress yield prediction DOI Creative Commons
Zongpeng Li, Xinguo Zhou,

Qian Cheng

et al.

Frontiers in Plant Science, Journal Year: 2023, Volume and Issue: 14

Published: Dec. 4, 2023

The timely and precise prediction of winter wheat yield plays a critical role in understanding food supply dynamics ensuring global security. In recent years, the application unmanned aerial remote sensing has significantly advanced agricultural research. This led to emergence numerous vegetation indices that are sensitive variations. However, not all these universally suitable for predicting yields across different environments crop types. Consequently, process feature selection index sets becomes essential enhance performance models. study aims develop an integrated method known as PCRF-RFE, with focus on selection. Initially, building upon prior research, we acquired multispectral images during flowering grain filling stages identified 35 yield-sensitive indices. We then applied Pearson correlation coefficient (PC) random forest importance (RF) methods select relevant features set. Feature filtering thresholds were set at 0.53 1.9 respective methods. union selected by both was used recursive elimination (RFE), ultimately yielding optimal subset constructing Cubist Recurrent Neural Network (RNN) results this demonstrate model, constructed using obtained through (PCRF-RFE), consistently outperformed RNN model. It exhibited highest accuracy stages, surpassing models or subsets derived from single method. confirms efficacy PCRF-RFE offers valuable insights references future research realms studies.

Language: Английский

Citations

1
Editorial: Plant-microbe interactions in forest ecosystems, volume II DOI Creative Commons
Julio Javier Díez, Ana Paula Moreira Rovedder, Luciano Kayser Vargas

et al.

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 15

Published: April 25, 2024

Language: Английский

Citations

0