This study investigated the impact of grassland and cropland expansion on carbon (C) and nitrous oxide (N₂O) emissions using remote sensing data and machine learning models. The research focused on agricultural land-use changes in South Sumatra from 1992 to 2018, utilizing Landsat satellite imagery and Google Earth Engine (GEE) for spatial and temporal analysis. Machine learning algorithms, including gradient boosting trees (GBT), random forest (RF), support vector machines (SVM), and classification and regression trees (CART), were employed to estimate greenhouse gas emissions based on multiple environmental parameters. These parameters include enhanced vegetation index (EVI), land surface temperature (LST), normalized difference vegetation index (NDVI), albedo, elevation, humidity, population density, precipitation, soil moisture, and wind speed. The results revealed a strong correlation between agricultural expansion and increased C and N₂O emissions, with RF and GBT models demonstrating superior predictive accuracy. Specifically, GBT and RF achieved the highest R² value (0.71, 0.59) and the lowest error metrics in modeling emissions, whereas SVM performed poorly across all cases. The study highlights the effectiveness of machine learning in quantifying emission dynamics and underscores the necessity of sustainable land management strategies to mitigate greenhouse gas emissions. By integrating remote sensing and data-driven methodologies, this research contributes to climate change mitigation policies and precision agriculture strategies aimed at balancing food security and environmental sustainability.

Soil erosion is a critical environmental issue that leads to land degradation, reduced agricultural productivity, and ecological imbalance. This study aims to assess soil loss under various land surface conditions by developing 11 distinct scenarios using the RUSLE (Revised Universal Soil Loss Equation) model integrated within the Google Earth Engine (GEE) platform. Remote sensing-derived indices including NDVI, EVI, NDWI, SAVI, and BSI were incorporated to represent vegetation cover, moisture, and bare/built-up surfaces. The K, LS, P, and R factors were held constant, allowing the C factor to vary based on each index, simulating real-world landscape differences. Soil loss maps were generated for each scenario, and spatial variability was analyzed using bubble charts, bar graphs, and C-map visualizations. The results show that vegetation-based indices such as NDVI and EVI lead to significantly lower soil loss estimations, while indices associated with built-up or bare surfaces like BSI predict higher erosion risks. These findings highlight the strong relationship between land cover characteristics and erosion intensity. This study demonstrates the utility of integrating satellite-based indices into erosion modeling and provides a scenario-based framework for supporting land management and soil conservation practices. The proposed approach can aid policymakers and land managers in prioritizing conservation efforts and mitigating erosion risk. Moreover, maintaining and enhancing vegetative cover is emphasized as a key strategy for promoting sustainable land use and long-term ecological resilience.

While air pollution poses a major threat to environmental health, monitoring and understanding this problem is extremely important. Especially in industrial areas, it is a vital requirement to monitor the levels of pollutants such as Nitrogen Dioxide (NO2), Sulphur Dioxide (SO2), Ozone (O3), Formaldehyde (HCHO) and Carbon Monoxide (CO) in the atmosphere. This situation becomes even more critical in areas such as Zonguldak where industrial activities are intense. In this study, the Sentinel-5P TROPOMI satellite and Google Earth Engine (GEE) platform were used to determine the air quality values in Zonguldak province. The study extracted data using coding method to determine the values of pollutants such as NO2, SO2, O3, HCHO and CO in the atmosphere between 2020 and-2022. Coding was performed using satellite data on the GEE platform and thematic maps and graphs were created with the data obtained. According to the results obtained, it was observed that air pollution is intense especially in Ereğli district and Filyos town. Such analyses are extremely important in terms of understanding the pollution levels in certain regions and evaluating their possible environmental impacts. These findings can provide important clues for taking protective measures for environmental health and reducing the effects of industrial activities on the environment.

Climate change mitigation relies heavily on understanding carbon storage dynamics in terrestrial ecosystems. This study examines the relationship between carbon storage (kg/m²) and various climatic variables, including precipitation, temperature, humidity, and radiation. Machine learning models such as Random Forest (RF), Gradient Tree Boost (GTB), Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Multiple Regression (MR) were applied. Among these, Random Forest exhibited the highest explanatory power (R² = 0.95, Adj. R² = 0.75, F-score = 4.721, Accuracy = 0.67), while ANN showed the highest predictive accuracy (Accuracy = 0.80). The results underline the significant role of climatic factors in shaping carbon dynamics, emphasizing the integration of machine learning-based models in carbon capture and sequestration (CCS) strategies. Furthermore, carbon storage dynamics in Utah from 1991 to 2020 were analyzed using remote sensing data and multiple regression models. Carbon storage was found to be highest in forested areas, wetlands, and natural grasslands, while agricultural and wildfire-affected zones exhibited lower carbon stocks. Climatic factors, particularly precipitation, temperature, and humidity, were identified as significant drivers of carbon sequestration, with moderate precipitation and favorable temperatures enhancing carbon retention. The study highlights the importance of region-specific CCS strategies, which rely on accurate climate-driven carbon storage assessments, for ensuring sustainable resource management and mitigating anthropogenic climate impacts.

Emissions from mines are important, but have not been sufficiently characterised to date. Air pollutant emissions from underground mine, and gases from industrial plant sites where large quantities of coal are stored, adversely affect the environment and human health and contribute to climate change. In this study, the emission distribution structure of atmosphere free methane gas from three ventilation systems of the underground production area within the borders of Kilimli district of Zonguldak Hard Coal Basin located in the Northwest region of Turkey and methane outflows in coal storage areas from five thermal power plants in the basin were analysed with Sentinel-5p TROPOMI satellite sensor data from Google Earth Engine (GEE) Platform for the years 2019–2023. For the conversion of TROPOMI sensor values in Mol/m² unit to gas outlet flow rate values in m³/min unit, CH₄ flow rate measurement data from the sensors at the emission outlet points of the Turkish Hard Coal Authority (TTK) were used. R² = 0.5601 and r = 0.75 correlation values were obtained from 13 common observations with a linear regression model. At the underground emission exit points, 5-year average flow rate values of 2.71 m³/min at Arslan Garden (ASB), 2.77 m³/min at exit point 140 and 2.79 m³/min at exit point 52 were calculated with the transformed TROPOMI data. Accordingly, it was determined that an average of 4,346 Million m³ of methane gas was released into the atmosphere annually and 21,730 Million m³ of methane gas was released in a total of five years.