The use of random forest to identify climate and human interference on vegetation coverage changes in southwest China

Ecological Indicators, Год журнала: 2022, Номер 144, С. 109463 - 109463

Опубликована: Сен. 19, 2022

Identifying vegetation changes and the associated driving forces provides a valuable reference for developing ecological restoration strategies. However, it remains challenge to disentangle impacts of climate, vegetation, human interference on changes. In this study, temporal variations Normalized Difference Vegetation Index (NDVI) during 2000–2015 in space were used identify greening (restoration) browning (degradation) areas southwest China. The Random Forest (RF) approach was applied distinguish main areas. Results showed that RF can be effectively learn complex non–linear interactions between change, local interferences. prominent 85.90 % study area, while 5.59 area still experienced significant degradation. Population pressure an important factor alter sign long-term trends. trends are mainly observed high elevation with low population density (e.g., lower than 180 people/km2 altitude above 1000 m), which attributed both artificial reforestation measures climate warming. contrast, trend concentrated temporally intensified due urbanization (over people/km2) increased rate 20 per year). results strengthen our understanding convolutions among activities,

Язык: Английский

---

The Carbon Sink Potential of Southern China After Two Decades of Afforestation

Earth s Future, Год журнала: 2022, Номер 10(12)

Опубликована: Ноя. 18, 2022

Afforestation and land use changes that sequester carbon from the atmosphere in form of woody biomass have turned southern China into one largest sinks globally, which contributes to mitigating climate change. However, forest growth saturation available can be forested limit longevity this sink, while a plethora studies quantified vegetation over last decades, remaining sink potential area is currently unknown. Here, we train model with multiple predictors characterizing heterogeneous landscapes predict carrying capacity region for 2002-2017. We compare observed predicted density find during about two decades afforestation, 2.34 PgC been sequestered between 2002 2017, total 5.32 Pg potentially still sequestrated. This means has reached 73% its aboveground 12% more than 2002, equal decrease 0.77% per year. identify afforestation areas 2.39 PgC, old new forests 87% their 1.85 remaining. Our work locates where not yet full but also shows long-term solution change mitigation.

Язык: Английский

---

Monitoring vegetation sensitivity to drought events in China

The Science of The Total Environment, Год журнала: 2023, Номер 893, С. 164917 - 164917

Опубликована: Июнь 15, 2023

Язык: Английский

---

The impact of climate change and human activities to vegetation carbon sequestration variation in Sichuan and Chongqing

Environmental Research, Год журнала: 2023, Номер 238, С. 117138 - 117138

Опубликована: Сен. 15, 2023

Язык: Английский

---

Spatiotemporal distribution and driving factors of regional green spaces during rapid urbanization in Nanjing metropolitan area, China

Ecological Indicators, Год журнала: 2023, Номер 148, С. 110058 - 110058

Опубликована: Март 1, 2023

In China, regional green spaces (RGSs) are outside urban built-up areas and have a wide distribution, large scale, outstanding ecological function. RGSs become increasingly important as clusters expand increase in number. However, studies on rare it remains unclear what drives their distribution the context of rapid urbanization. This study used integrated approaches to explore driving factors Nanjing metropolitan area (NMA) between 2000 2020, using Landsat image data. Spatiotemporal variations were obtained net change rate index standard deviational ellipse. The identified Pearson correlation, ordinary least squares (OLS), geographically weighted regression (GWR). We found that: (1) More south NMA, less north region. A "V" pattern was observed, with substantial losses shifting from Yangtze River coastline hilly mountainous regions 2020. (2) affected by combination physical geographic, socioeconomic, policy management factors. functions these influencing pronounced spatiotemporal heterogeneity direction or magnitude. Physical geographic including slope annual precipitation exhibited strongest correlation coefficients showed relatively stable spatial performance. Among socioeconomic factors, distance GDP played an role. Policy has guiding role, positive influence generated dedicated financial expenditure statutory space tends maintain balance. results this can help further understand provide theoretical support for construction during

Язык: Английский

---

Assessing vegetation resilience and vulnerability to drought events in Central Asia

Journal of Hydrology, Год журнала: 2024, Номер 634, С. 131012 - 131012

Опубликована: Март 7, 2024

Язык: Английский

---

Prediction and Spatiotemporal Dynamics of Vegetation Index Based on Deep Learning and Environmental Factors in the Yangtze River Basin

Forests, Год журнала: 2025, Номер 16(3), С. 460 - 460

Опубликована: Март 5, 2025

Accurately predicting the vegetation index (VI) of Yangtze River Basin and analyzing its spatiotemporal trends are essential for assessing dynamics providing recommendations environmental resource management in region. This study selected key climate factors most strongly correlated with three indexes (VI): Normalized Difference Vegetation Index (NDVI), Enhanced (EVI), kernel (kNDVI). Historical VI data (2001–2020) were used to train, validate, test a CNN-BiLSTM-AM deep learning model, which integrates strengths Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), Attention Mechanism (AM). The performance this model was compared CNN-BiLSTM, LSTM, BiLSTM-AM models validate superiority VI. Finally, simulation under Shared Socioeconomic Pathway (SSP) scenarios (SSP1-1.9, SSP2-4.5, SSP5-8.5) as inputs predict next 20 years (2021–2040), aiming analyze trends. results showed following: (1) Temperature, precipitation, evapotranspiration had highest correlation time series model. (2) combined EVI achieved best (R2 = 0.981, RMSE 0.022, MAE 0.019). (3) Under all scenarios, over an upward trend previous years, significant growth observed SSP5-8.5. source region western part upper reaches increased slowly, while increases eastern reaches, middle lower estuary. analysis predicted indicates that conditions will continue improve years.

Язык: Английский

---

Relationship between net primary production and climate change in different vegetation zones based on EEMD detrending – A case study of Northwest China

Ecological Indicators, Год журнала: 2020, Номер 122, С. 107276 - 107276

Опубликована: Дек. 21, 2020

The relationship between vegetation Net primary production (NPP) and climate change is critical for understanding the driving forces of changes, while less were studied based on detrending analysis Bioclimatic variables. In this study, Ensemble Empirical Mode Decomposition (EEMD) method was adopted to assess NPP in different zones Northwest China. results indicated that: (1) although monotonic increasing main type trend (49.42%), shifted accounted 36.02% whole area. There some risks degradation temperate desert alpine region Qinghai Tibet Platea, but chances recovery grassland warm deciduous broad-leaved forest zones; (2) EEMD-detrending performed much better than linear assessing NPP; (3) compared with no detrending, reduced importance BIO1 (annual mean temperature) BIO2 (mean temperature diurnal range) NPP, enhanced those BIO13 (precipitation wettest month) BIO15 seasonality); (4) BIO1, BIO2, BIO12 precipitation), mainly showed positive relationships interannual variations, except that negative zones. Interannual variations dominated by BIO13, plateau BIO2. Our demonstrated variables can explore vegetation-climate relationship.

Язык: Английский

---

Quantification of Natural and Anthropogenic Driving Forces of Vegetation Changes in the Three-River Headwater Region during 1982–2015 Based on Geographical Detector Model

Remote Sensing, Год журнала: 2021, Номер 13(20), С. 4175 - 4175

Опубликована: Окт. 19, 2021

The three-river headwater region (TRHR) supplies the Yangtze, Yellow, and Lantsang rivers, its ecological environment is fragile, hence it important to study surface vegetation cover status of TRHR facilitate conservation. normalized difference index (NDVI) can reflect vegetation. aims this are quantify spatial heterogeneity NDVI, identify main driving factors influencing explore interaction between these factors. To end, we used global inventory modeling mapping studies (GIMMS)-NDVI data from 1982 2015 included eight natural (namely slope, aspect, elevation, soil type, landform annual mean temperature, precipitation) three anthropogenic (gross domestic product (GDP), population density, land use type), which subjected linear regression analysis, Mann-Kendall statistical test, moving t-test analyze temporal variability NDVI in over 34 years, using a geographical detector model. Our results showed that distribution was high southeast low northwest. change pattern exhibited an increasing trend west north decreasing center south; overall, value has increased. Annual precipitation most factor changes TRHR, factors, such as also explained coverage well. influence generally stronger than had synergistic effect, exhibiting mutual enhancement nonlinear relationships. provide insights into conservation security development middle lower reaches.

Язык: Английский

---

Spatiotemporal analysis and potential impact factors of vegetation variation in the karst region of Southwest China

Environmental Science and Pollution Research, Год журнала: 2021, Номер 28(43), С. 61258 - 61273

Опубликована: Июнь 25, 2021

Язык: Английский

---