Historical and projected changes in Extreme High Temperature events over East Africa and associated with meteorological conditions using CMIP6 models

Global and Planetary Change, Journal Year: 2023, Volume and Issue: 222, P. 104068 - 104068

Published: Feb. 17, 2023

Language: Английский

---

The utility of Planetscope spectral data in quantifying above-ground carbon stock in an urban reforested landscape

Ecological Informatics, Journal Year: 2024, Volume and Issue: 80, P. 102472 - 102472

Published: Jan. 20, 2024

Language: Английский

---

Increases in extreme precipitation expected in Northeast China under continued global warming

Climate Dynamics, Journal Year: 2024, Volume and Issue: 62(6), P. 4943 - 4965

Published: March 21, 2024

Language: Английский

---

A Survey of Computer Vision Techniques for Forest Characterization and Carbon Monitoring Tasks

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(22), P. 5861 - 5861

Published: Nov. 19, 2022

Estimation of terrestrial carbon balance is one the key tasks in understanding and prognosis climate change impacts development tools policies according to mitigation adaptation strategies. Forest ecosystems are major pools stocks affected by controversial processes influencing stability. Therefore, monitoring forest a proper inventory management resources planning their sustainable use. In this survey, we discuss which computer vision techniques applicable most important aspects actions, considering wide availability remote sensing (RS) data different resolutions based both on satellite unmanned aerial vehicle (UAV) observations. Our analysis applies occurring such as estimation areas, tree species classification, resources. Through also provide necessary technical background with description suitable sources, algorithms’ descriptions, corresponding metrics for evaluation. The implementation provided into routine workflows significant step toward systems continuous actualization data, including real-time monitoring. It crucial diverse purposes local global scales. Among improved strategies offset projects, enhancement prediction accuracy system changes under land-use scenarios.

Language: Английский

---

Combining Sample Plot Stratification and Machine Learning Algorithms to Improve Forest Aboveground Carbon Density Estimation in Northeast China Using Airborne LiDAR Data

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(6), P. 1477 - 1477

Published: March 18, 2022

Timely, accurate estimates of forest aboveground carbon density (AGC) are essential for understanding the global cycle and providing crucial reference information climate-change-related policies. To date, airborne LiDAR has been considered as most precise remote-sensing-based technology AGC estimation, but it suffers great challenges from various uncertainty sources. Stratified estimation potential to reduce improve estimation. However, impact stratification how effectively combine modeling algorithms have not fully investigated in In this study, we performed a comparative analysis different approaches (non-stratification, type (FTS) dominant species (DSS)) (stepwise regression, random (RF), Cubist, extreme gradient boosting (XGBoost) categorical (CatBoost)) identify optimal approach algorithm using data. The variance (ANOVA) was used quantify determine factors that had significant effect on accuracy. results revealed superiority stratified models over unstratified ones, with higher accuracy achieved by DSS models. Moreover, improvement more coniferous than broadleaf species. ML outperformed stepwise regression CatBoost based provided highest (R2 = 0.8232, RMSE 5.2421, RRMSE 20.5680, MAE 4.0169 Bias 0.4493). ANOVA prediction error indicated method important factor This study demonstrated positive combination can AGC. Integrating strategy national inventory could help monitoring stock large areas.

Language: Английский

---

Drought Assessment on Vegetation in the Loess Plateau Using a Phenology-Based Vegetation Condition Index

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(13), P. 3043 - 3043

Published: June 24, 2022

Frequent droughts induced by climate warming have caused increasing impacts on the vegetation of Loess Plateau (LP). However, effects drought are highly dependent when occurs and how long it lasts during growing season. Unfortunately, most existing indices ignore differences in different growth stages. In this study, we first established a phenology-based condition index, namely weighted index (WVCI), which accounts for sensitivity to assigning specific weights phenological stages vegetation. Then, used WVCI reveal temporal spatial variations vegetative from 2001 2019 over LP aspects frequency, trend relative deviation. The results showed that (1) experienced frequent study period, but mainly mild moderate droughts. frequencies decreased southeast northwest, extreme rarely occurred mountainous areas plains. (2) tended ease, only few Hetao Plain, Ningxia Plain Fenwei an drought. (3) After 2012, departure percentage was positive, indicating above-average conditions. (4) Compared with well-established proved ability monitor assess annual scale LP. As result, our research could help develop implement drought-resistance disaster-prevention measures

Language: Английский

---

An explicit forest carbon stock model and applications

Geo-spatial Information Science, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 12

Published: March 10, 2025

Language: Английский

---

Evaluating k-Nearest Neighbor (kNN) Imputation Models for Species-Level Aboveground Forest Biomass Mapping in Northeast China

Remote Sensing, Journal Year: 2019, Volume and Issue: 11(17), P. 2005 - 2005

Published: Aug. 25, 2019

Quantifying spatially explicit or pixel-level aboveground forest biomass (AFB) across large regions is critical for measuring carbon sequestration capacity, assessing balance, and revealing changes in the structure function of ecosystems. When AFB measured at species level using widely available remote sensing data, regional composition can readily be monitored. In this study, wall-to-wall maps species-level were generated forests Northeast China by integrating inventory data with Moderate Resolution Imaging Spectroradiometer (MODIS) images environmental variables through applying optimal k-nearest neighbor (kNN) imputation model. By comparing prediction accuracy 630 kNN models, we found that models random (RF) as distance metric showed highest accuracy. Compared to use single-month MODIS September, there was no appreciable improvement estimation multi-month data. k > 7, RF-based single predictors September essentially negligible. Therefore, model RF metric, (September) = 7 impute entire China. Our results average all over 101.98 Mg/ha around 2000. Among 17 widespread species, larch most dominant, largest (20.88 Mg/ha), followed white birch (13.84 Mg/ha). Amur corktree willow had low (0.91 0.96 Mg/ha, respectively). Environmental (e.g., climate topography) strong relationships AFB. complete spatial coverage model, successfully mapped distribution tree We also evaluated different scales. The significantly improved from stand up ecotype level, indicating study are more suitable apply ecosystem LINKAGES) which require attributes scale.

Language: Английский

---

The impact of heterogeneous distance functions on missing data imputation and classification performance

Engineering Applications of Artificial Intelligence, Journal Year: 2022, Volume and Issue: 111, P. 104791 - 104791

Published: March 24, 2022

Language: Английский

---

Developing machine learning models with multiple environmental data to predict stand biomass in natural coniferous-broad leaved mixed forests in Jilin Province of China

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 212, P. 108162 - 108162

Published: Aug. 24, 2023

Language: Английский

---