Spatial information about the soil is needed increasingly for making informed management decisions about the environment, particularly with regard to developing different types of agriculture. In this project, machine learning models are used to quantify the spatial distribution of soils on local, regional, and national scales based on the relationships between environmental data and soil properties/classes. [**article1**](https://www.sciencedirect.com/science/article/abs/pii/S0016706119312777),[**article2**](https://www.sciencedirect.com/science/article/abs/pii/S0016706121001889?via%3Dihub),[**article3**](https://www.sciencedirect.com/science/article/abs/pii/S0016706122004013?via%3Dihub).
Soil degradations are predominant environmental problem world-wide their accurate assessment is essential for determining appropriate ways to deal with land degradation, for better soil and crop management. In this project, the applicability of machine learning models and remote sensing is evaluated to monitor and assess land degradations such as soil salinity, soil erosion, and air/water/soil pollution. [**article1**](https://www.sciencedirect.com/science/article/abs/pii/S0016706120325489?via%3Dihub),[**article2**](https://www.sciencedirect.com/science/article/abs/pii/S0016706117314003?via%3Dihub),[**article3**](https://www.sciencedirect.com/science/article/abs/pii/S1309104221001306?via%3Dihub).
Soil organic carbon storage is a key function of soils, influencing soil physicochemical properties. As the world’s soils contain more organic carbon than the atmosphere and the biosphere together, soils are considered to be a crucial pool in the global carbon cycle. Thus, accurate spatial information of SOC is vital to estimate and predict greenhouse gas emissions and physicochemical functions of soils. [**article1**](https://www.mdpi.com/2072-4292/12/7/1095),[**article2**](https://www.tandfonline.com/doi/full/10.1080/17583004.2017.1330593),[**article3**](https://www.sciencedirect.com/science/article/pii/S0016706115301543).
An increasing amount of sophisticated data, from remote sensing and especially from proximal sensing, make it possible to bridge the gap between data and decisions within agricultural planning. On-demand representative sampling and modeling of useful soil information leads to an improvement in the decision-making processes of fertilization, higher productivity, and biofuel production. [**article1**](https://www.mdpi.com/2073-4395/10/4/573),[**article2**](https://www.sciencedirect.com/science/article/abs/pii/S0341816221006937?via%3Dihub),[**article3**](https://www.sciencedirect.com/science/article/pii/S0167198718314302).