Assessing the Productivity of the Matang Mangrove Forest Reserve: Review of One of the Best-Managed Mangrove Forests

Forests, Journal Year: 2024, Volume and Issue: 15(5), P. 747 - 747

Published: April 25, 2024

Mangrove ecosystems are crucial for biodiversity and coastal protection but face threats from climate change human activities. This review assesses the productivity of Matang Forest Reserve (MMFR) in Malaysia, which is recognised as one best-managed mangrove forests, while also addressing challenges such deforestation change-induced factors. explores concept highlighting their role carbon sequestration discussing litterfall measurements fundamental metrics assessing primary productivity. An analysis historical changes MMFR’s biomass revealed fluctuations influenced by logging, reforestation, climatic conditions. Trends MMFR indicate a concerning decline attributed to anthropogenic activities aquaculture industrial projects. A regression conducted on Rhizophora apiculata data with age predictor AGB response variable indicated positive trend (slope = 3.61, R-squared 0.686), suggesting quantitative increase age. Further significant negative overall over years (coefficient −3.974, p < 0.05) strong inverse relationship (rho −0.818, 0.05), indicating declining trends. Despite these challenges, this underscores significance sustainable management practices, effective conservation efforts, community engagement maintaining ecosystem health In conclusion, sharing lessons can contribute global forest fostering resilience vital ecosystems.

Language: Английский

---

Comparing machine learning algorithms to predict vegetation fire detections in Pakistan

Fire Ecology, Journal Year: 2024, Volume and Issue: 20(1)

Published: June 24, 2024

Abstract Vegetation fires have major impacts on the ecosystem and present a significant threat to human life. consists of forest fires, cropland other vegetation in this study. Currently, there is limited amount research long-term prediction Pakistan. The exact effect every factor frequency remains unclear when using standard analysis. This utilized high proficiency machine learning algorithms combine data from several sources, including MODIS Global Fire Atlas dataset, topographic, climatic conditions, different types acquired between 2001 2022. We tested many ultimately chose four models for formal processing. Their selection was based their performance metrics, such as accuracy, computational efficiency, preliminary test results. model’s logistic regression, random forest, support vector machine, an eXtreme Gradient Boosting were used identify select nine key factors and, case vegetation, seven that cause fire findings indicated achieved accuracies ranging 78.7 87.5% 70.4 84.0% 66.6 83.1% vegetation. Additionally, area under curve (AUC) values ranged 83.6 93.4% 72.6 90.6% 74.2 90.7% model had highest accuracy rate also AUC value proving be most optimal model. provided predictive insights into specific conditions regional susceptibilities occurrences, adding beyond initial detection data. maps generated analyze Pakistan’s risk showed geographical distribution areas with high, moderate, low risks, highlighting assessments rather than historical detections.

Language: Английский

---

Assessing Forest Fragmentation due to Land use Changes from 1992 to 2023: A Spatio-Temporal Analysis Using Remote Sensing Data

Heliyon, Journal Year: 2024, Volume and Issue: 10(14), P. e34710 - e34710

Published: July 1, 2024

The increasing pressures of urban development and agricultural expansion have significant implications for land use cover (LULC) dynamics, particularly in ecologically sensitive regions like the Murree Kotli Sattian tehsils Rawalpindi district Pakistan. This study's primary objective is to assess spatial variations within each LULC category over three decades (1992-2023) using cross-tabulation ArcGIS identify changes investigates into forest fragmentation analysis Landscape Fragmentation Tool (LFTv2.0) classify several classes such as patch, edge, perforated, small core, medium large core. Utilizing remote sensing data from Landsat 5 9 satellites, research focuses on temporal dynamics various including Coniferous Forest (CF), Evergreen (EF), Arable Land (AR), Buildup Area (BU), Barren (BA), Water (WA), Grassland (GL). Support Vector Machine (SVM) classifier software were employed image processing classification, ensuring accuracy categorizing different types. Our results indicate a notable reduction forested areas, with (CF) decreasing 363.9 km

Language: Английский

---

Comparative analysis of sensors and classification algorithms for land cover classification in Islamabad, Pakistan

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(2)

Published: Jan. 29, 2025

Language: Английский

---

Advancing forest fire prediction: A multi-layer stacking ensemble model approach

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(3)

Published: Feb. 19, 2025

Language: Английский

---

Monitoring and prediction of the LULC change dynamics using time series remote sensing data with Google Earth Engine

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2024, Volume and Issue: 136, P. 103689 - 103689

Published: Aug. 9, 2024

Language: Английский

---

Analysis of vegetation dynamics from 2001 to 2020 in China's Ganzhou rare earth mining area using time series remote sensing and SHAP-enhanced machine learning

Ecological Informatics, Journal Year: 2024, Volume and Issue: 84, P. 102887 - 102887

Published: Nov. 9, 2024

Language: Английский

---

Spatiotemporal analysis of surface Urban Heat Island intensity and the role of vegetation in six major Pakistani cities

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102986 - 102986

Published: Dec. 1, 2024

Language: Английский

---

Integrating RUSLE Model with Cloud-Based Geospatial Analysis: A Google Earth Engine Approach for Soil Erosion Assessment in the Satluj Watershed

Water, Journal Year: 2024, Volume and Issue: 16(8), P. 1073 - 1073

Published: April 9, 2024

This study employed an advanced geospatial methodology using the Google Earth Engine (GEE) platform to assess soil erosion in Satluj Watershed thoroughly. To achieve this, Revised Universal Soil Loss Equation (RUSLE) model was integrated into study, which revealed through several analytical tiers, each with a unique function. The commenced estimating R factor, carried out annual precipitation data from Climate Hazards Group Infra-Red Precipitation Station (CHIRPS). erodibility of soil, K factor describes, then calculated USDA texture classifications taken Open Land Map. third layer emphasizes LS analyzes slope and how they affect rates, digital elevation models. understand impact vegetation on conservation, fourth presents C evaluates changes land cover, Normalized Difference Vegetation Index (NDVI) derived Sentinel-2 data. P incorporates MODIS types cover conditions. Combining these layers RUSLE produces thorough loss map, revealing different levels throughout Watershed. preliminary findings indicate that 3.3% watershed had slight loss, 0.2% moderate 1.2% high rates. And 92% severe rates erosion. After investigation, detected regions were divided risk classifications, providing vital information for watershed’s management conservation plans. mean determined be 10,740 tons/ha/year. novel method creates strong foundation evaluating erosion, while also highlighting value cloud-based analysis comprehending intricate environmental processes.

Language: Английский

---

Inferring the relationship between soil temperature and the normalized difference vegetation index with machine learning

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

Published: July 20, 2024

Language: Английский

---