Search

This study proposes a machine learning based methodology for estimating Arctic thin sea ice thickness (up to 1 m) from brightness temperature measurements of SMOS. The approach involves employing the so-called Burke model for sea ice emission modeling, integrating a suitable permittivity model and a radiative transfer equation. The training dataset is generated through a model-based simulation, and is then used to train and evaluate two machine learning regression algorithms: Random Forest and Gradient Boosting. Overall, this machine learning methodology results in great agreement with the ESA's official sea ice thickness product. Additionally, a validation performed by using data from mooring measurements shows a subtle improvement by the machine learning algorithms with respect to the ESA's official product. These results indicate their potential to surpass the performance of the current SMOS thin sea ice thickness retrievals.

Maps of irrigation systems are of critical value for a better understanding of the human impact on the water cycle, while they also present a very useful tool at the administrative level to monitor changes and optimize irrigation practices. This study proposes a novel approach for classifying different irrigation systems at field level by using remotely sensed data at subfield scale as inputs of different supervised machine learning (ML) models for time-series classification. The ML models were trained using ground-truth data from more than 300 fields collected during a field campaign in 2020 across an intensely cultivated region in Catalunya, Spain. Two hydrological variables retrieved from satellite data, actual evapotranspiration ($ET_{a}$) and soil moisture ($SM$), showed the best results when used for classification, especially when combined together, retrieving a final accuracy of $90.1 \pm 2.7\%$. All the three ML models employed for the classification showed that they were able to distinguish different irrigation systems, regardless of the different crops present in each field. For all the different tests, the best performances were reached by ResNET, the only deep neural network model among the three tested. The resulting method enables the creation of maps of irrigation systems at field level and for large areas, delivering detailed information on the status and evolution of irrigation practices.