Integration of machine learning and remote sensing for above ground biomass estimation through Landsat-9 and field data in temperate forests of the Himalayan region

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102732 - 102732

Published: July 22, 2024

Accurately estimating aboveground biomass (AGB) in forest ecosystems facilitates efficient resource management, carbon accounting, and conservation efforts. This study examines the relationship between predictors from Landsat-9 remote sensing data several topographical features. While provides reliable crucial for long-term monitoring, it is part of a broader suite available technologies. We employ machine learning algorithms such as Extreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), Random Forest (RF), alongside linear regression techniques like Multiple Linear (MLR). The primary objectives this encompass two key aspects. Firstly, research methodically selects optimal predictor combinations four distinct variable groups: (L1) data, fusion Vegetation-based indices (L2), integration with Shuttle Radar Topography Mission Digital Elevation Model (SRTM DEM) (L3) combination best (L4) derived L1, L2, L3. Secondly, systematically assesses effectiveness different to identify most precise method establishing any potential field-measured AGB variables. Our revealed that (RF) model was utilizing OLI SRTM DEM predictors, achieving remarkable accuracy. conclusion reached by assessing its outstanding performance when compared an independent validation dataset. RF exhibited accuracy, presenting relative mean absolute error (RMAE), root square (RRMSE), R2 values 14.33%, 22.23%, 0.81, respectively. XGBoost subsequent choice RMAE, RRMSE, 15.54%, 23.85%, 0.77, further highlights significance specific spectral bands, notably B4 B5 Landsat 9 capturing spatial distribution patterns. Integration vegetation-based indices, including TNDVI, NDVI, RVI, GNDVI, refines mapping precision. Elevation, slope, Topographic Wetness Index (TWI) are proxies representing biophysical biological mechanisms impacting AGB. Through utilization openly accessible fine-resolution employing algorithm, demonstrated promising outcomes identification predictor-algorithm mapping. comprehensive approach offers valuable avenue informed decision-making assessment, ecological monitoring initiatives.

Language: Английский

---

Assessing Chilgoza Pine (Pinus gerardiana) forest fire severity: Remote sensing analysis, correlations, and predictive modeling for enhanced management strategies

Trees Forests and People, Journal Year: 2024, Volume and Issue: 16, P. 100521 - 100521

Published: Feb. 24, 2024

Forest fires represent a critical global threat to both humans and ecosystems. This study examines the intensity impacts of Chilgoza (Pinus gerardiana) Pine by using advanced remote sensing techniques comprising Normalized Burn Ratio (NBR) Difference (dNBR) analyses based on Landsat 9 datasets. The highlights severe effect these fires, resulting in noteworthy losses livestock private properties widespread damage 10,156.53 acres Forest. A comprehensive variable correlation analysis is conducted gain deeper insights into influencing factors causing forest fires. Spearman's Rank Correlation Coefficient was used assess association between burnt unburnt areas various independent factors. reveals compelling evidence significant correlations with fire prevalence. found moderate negative (-0.532, p < 0.05) positive (0.513, elevation Land Surface Temperature (LST), respectively, weak (0.252, Wind Speed (V). To predict susceptibility better understand contributing factors, three machine learning models, Random (RF), XGBoost, logistic regression, are applied importance scores. Among considered LST most variable, consistently high scores (100%, 96%, 59%) across all models. (V) also proved influential 78%, 83%, 61% for RF, respectively. Moreover, significantly influences frequency as evidenced ranging from 26% 100%. Comparatively, model outperforms XGBoost Logistic Regression predicting vulnerability. During training stage, (RF) achieves an impressive classification accuracy 99.1%, followed 94.5% 85.6%. On evaluation validation dataset, accuracies remain promising, RF at 96.4%, 91.1%, 84.6%. Based model, identified high-risk sites offer valuable proactive management prevention strategies. provides robust predictive understanding severity impacts. Future research should consider climate change scenarios account human activities enhance behavior predictions risk assessment

Language: Английский

---

Analyzing vegetation health dynamics across seasons and regions through NDVI and climatic variables

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: May 23, 2024

Abstract This study assesses the relationships between vegetation dynamics and climatic variations in Pakistan from 2000 to 2023. Employing high-resolution Landsat data for Normalized Difference Vegetation Index (NDVI) assessments, integrated with climate variables CHIRPS ERA5 datasets, our approach leverages Google Earth Engine (GEE) efficient processing. It combines statistical methodologies, including linear regression, Mann–Kendall trend tests, Sen's slope estimator, partial correlation, cross wavelet transform analyses. The findings highlight significant spatial temporal NDVI, an annual increase averaging 0.00197 per year (p < 0.0001). positive is coupled precipitation by 0.4801 mm/year = 0.0016). In contrast, analysis recorded a slight decrease temperature (− 0.01011 °C/year, p 0.05) reduction solar radiation 0.27526 W/m 2 /year, 0.05). Notably, cross-wavelet underscored coherence NDVI factors, revealing periods of synchronized fluctuations distinct lagged relationships. particularly highlighted as primary driver growth, illustrating its crucial impact across various Pakistani regions. Moreover, revealed seasonal patterns, indicating that health most responsive during monsoon season, correlating strongly peaks precipitation. Our investigation has Pakistan's complex association which varies different Through analysis, we have identified phase critical influence drivers on patterns. These insights are developing regional adaptation strategies informing sustainable agricultural environmental management practices face ongoing changes.

Language: Английский

---

Analysing LULC transformations using remote sensing data: insights from a multilayer perceptron neural network approach

Annals of GIS, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 28

Published: May 4, 2024

The study examines the complex dynamics of changes in LULC over three decades, focused on years 1992, 2002, 2012, and 2022. research highlights significance comprehending these alterations within framework environmental socio-economic consequences. land use cover (LULC) have significant far-reaching effects ecosystems, biodiversity, human livelihoods. This offers useful information for politicians, conservationists, urban planners by examining historical patterns forecasting future changes. utilized a Multilayer Perceptron Neural Network (MLP-NN), well-known machine learning technique that excels at collecting intricate patterns. model's design had layers: input, hidden, output. model underwent 10,000 iterations during its training process, thorough statistical analysis was conducted to assess impact each driving component. MLP-NN demonstrated impressive performance, with skill measure 0.8724 an accuracy rate 89.08%. estimates 2022 verified comparing them observed data, ensuring reliability. Moreover, presence evidence likely found be factor substantial model. effectiveness accurately predicting LULC. exceptional proficiency make it powerful tool forecasts. Identifying primary causes performance understanding their implications may help enhance management strategies, encourage spatial planning, guide accurate decision-making, facilitate development policies align sustainable growth development.

Language: Английский

---

Unveiling Fractional Vegetation Cover Dynamics: A Spatiotemporal Analysis Using MODIS NDVI and Machine Learning

Environmental and Sustainability Indicators, Journal Year: 2024, Volume and Issue: unknown, P. 100485 - 100485

Published: Sept. 1, 2024

Language: Английский

---

Assessment of climatic influences on net primary productivity along elevation gradients in temperate ecoregions

Trees Forests and People, Journal Year: 2024, Volume and Issue: 18, P. 100657 - 100657

Published: Aug. 20, 2024

Language: Английский

---

Spatiotemporal dynamics of vegetation cover: integrative machine learning analysis of multispectral imagery and environmental predictors

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(1)

Published: Jan. 1, 2025

Language: Английский

---

Assessing Spatiotemporal Dynamics of Net Primary Productivity in Shandong Province, China (2001–2020) Using the CASA Model and Google Earth Engine: Trends, Patterns, and Driving Factors

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(3), P. 488 - 488

Published: Jan. 30, 2025

Net primary productivity (NPP) is a core ecological indicator within terrestrial ecosystems, representing the potential of vegetation growth to offset anthropogenic carbon emissions. Thus, assessing NPP in given region crucial for promoting regional restoration and sustainable development. This study utilized CASA model GEE calculate annual average Shandong Province (2001–2020). Through trend analysis, Moran’s Index, PLS−SEM, spatiotemporal evolution driving factors were explored. The results show that: (1) From 2001 2020, showed an overall increasing trend, rising from 254.96 322.49 g C·m⁻2/year. shift was accompanied by gradual eastward movement centroid, indicating significant spatial changes productivity. (2) Regionally, 47.9% experienced improvement, 27.6% saw slight 20.1% exhibited degradation, highlighting notable heterogeneity. (3) Driver analysis that climatic positively influenced across all four periods (2005, 2010, 2015, 2020), with strongest impact 2015 (coefficient = 0.643). Topographic such as elevation slope also had positive effects, peaking at 0.304 2015. In contrast, human activities, especially GDP nighttime light intensity, negatively impacted NPP, negative effect 2010 −0.567). These findings provide valuable scientific evidence ecosystem management offer key insights development strategies national level.

Language: Английский

---

Machine Learning and Spatio Temporal Analysis for Assessing Ecological Impacts of the Billion Tree Afforestation Project

Ecology and Evolution, Journal Year: 2025, Volume and Issue: 15(2)

Published: Feb. 1, 2025

ABSTRACT This study evaluates the Billion Tree Afforestation Project (BTAP) in Pakistan's Khyber Pakhtunkhwa (KPK) province using remote sensing and machine learning. Applying Random Forest (RF) classification to Sentinel‐2 imagery, we observed an increase tree cover from 25.02% 2015 29.99% 2023 a decrease barren land 20.64% 16.81%, with accuracy above 85%. Hotspot spatial clustering analyses revealed significant vegetation recovery, high‐confidence hotspots rising 36.76% 42.56%. A predictive model for Normalized Difference Vegetation Index (NDVI), supported by SHAP analysis, identified soil moisture precipitation as primary drivers of growth, ANN achieving R 2 0.8556 RMSE 0.0607 on testing dataset. These results demonstrate effectiveness integrating learning framework support data‐driven afforestation efforts inform sustainable environmental management practices.

Language: Английский

---

Derivation of Allometric Equations and Carbon Content Estimation in Mangrove Forests of Malaysia

Environmental and Sustainability Indicators, Journal Year: 2025, Volume and Issue: unknown, P. 100618 - 100618

Published: Jan. 1, 2025

Language: Английский

---