Abstract

Recently, the increasing severity of climate change attributable to global warming has emphasized the imperative of carbon absorption to mitigate greenhouse gas emissions. The use of the carbon sink based on the carbon absorption and storage functions of forests is suggested as an effective alternative for domestic greenhouse gas reduction. Additionally, agricultural land cover comprises approximately 38% of the Earth's surface, underscoring the importance of comprehensively understanding the carbon cycle within not only forests but also agricultural landscapes. This significance arises from the fact that agricultural land locally amplifies seasonal variations in carbon dioxide by approximately 25% compared to vegetated areas. Consequently, a comprehensive understanding of both forest and agricultural land carbon cycles is imperative, necessitating quantitative analysis of carbon uptake in agricultural settings. Thus, this study aims to construct a machine learning-based model for estimating the net ecosystem exchange (NEE) of rice paddies in South Korea using ground flux data, meteorological variables, and satellite images. Through quantitative assessment, the NEE was determined, with a mean absolute error of 1.387, root mean square error of 2.203, and correlation coefficient of 0.872. Notably, observed NEE values demonstrating extremes in magnitude were associated with calculation errors, reflecting tendencies of both underestimation and overestimation. This phenomenon is likely attributed to the study's reliance on a limited dataset and the inherent challenges of training models across a broad spectrum of observations. To enhance calculation accuracy, future endeavors should focus on accumulating a more extensive repository of NEE flux observations and leveraging high-resolution satellite imagery and meteorological datasets for refining machine learningbased models.

Abstract

Recently, the increasing severity of climate change attributable to global warming has emphasized the imperative of carbon absorption to mitigate greenhouse gas emissions. The use of the carbon sink based on the carbon absorption and storage functions of forests is suggested as an effective alternative for domestic greenhouse gas reduction. Additionally, agricultural land cover comprises approximately 38% of the Earth's surface, underscoring the importance of comprehensively understanding the carbon cycle within not only forests but also agricultural landscapes. This significance arises from the fact that agricultural land locally amplifies seasonal variations in carbon dioxide by approximately 25% compared to vegetated areas. Consequently, a comprehensive understanding of both forest and agricultural land carbon cycles is imperative, necessitating quantitative analysis of carbon uptake in agricultural settings. Thus, this study aims to construct a machine learning-based model for estimating the net ecosystem exchange (NEE) of rice paddies in South Korea using ground flux data, meteorological variables, and satellite images. Through quantitative assessment, the NEE was determined, with a mean absolute error of 1.387, root mean square error of 2.203, and correlation coefficient of 0.872. Notably, observed NEE values demonstrating extremes in magnitude were associated with calculation errors, reflecting tendencies of both underestimation and overestimation. This phenomenon is likely attributed to the study's reliance on a limited dataset and the inherent challenges of training models across a broad spectrum of observations. To enhance calculation accuracy, future endeavors should focus on accumulating a more extensive repository of NEE flux observations and leveraging high-resolution satellite imagery and meteorological datasets for refining machine learningbased models.

Abstract

Climate change is a global problem that affects the state of conservation of ecosystems in all regions of the world; as well as in the Chimborazo Fauna Production Reserve, which is linked to anthropogenic activities inside and outside it, such as the extensive and intensive grazing of sheep and cattle that have caused effects on vegetation and soil given to the consumption of native plants and all ecosystem processes because they are related to each other. The methodology used to achieve optimal discrimination of vegetation change and conservation status is obtained through the application of satellite images LANDSAT 5, LANDSAT 7, orthophotos and aerial photographs from 1962 to 1966 up to 2010 distributed in three periods; using procedures such as supervised classification and the calculation of the Normalized Differential Index of Vegetation. Anthropogenic activity for the period 1962-1966 determines 0.26% and snow is 10.30%, while for the period 2010-2011, the percentage of intervention increases to 9.54% and the snow decreases to 4.46%, evidencing the loss of perpetual snow due to solar radiation.