A new study finds that commercial satellite imagery data often outperforms public data sets when identifying surface water, but that public data sets may be better at detecting water hidden by forest cover. Commercial satellite sata is typically higher resolution than freely available data, but certain free datasets make use of expanded spectral band imaging to detect water not visible to the human eye. 

Machine learning could significantly enhance personality testing by making assessments faster, more flexible and more accurate, according to new research from the University of East London. Analysing DISC assessment data from over 1,000 participants, the study found AI models could replicate traditional classifications with over 93% accuracy while also identifying blended personality traits often missed by standard methods. Researchers also showed that a streamlined 10-question version of the test could retain more than 91% accuracy, offering a quicker yet reliable alternative for use in recruitment, leadership development and team building.

Peri-urban agriculture in the Barcelona Metropolitan Area (AMB) is in a critical situation after decades of decline. A new study conducted by the Institute of Environmental Science and Technology of the Universitat Autònoma de Barcelona (ICTA-UAB) highlights the dramatic reduction of peri-urban farming in the region, with losses of up to 70% of agricultural land, largely driven by urban expansion, real estate speculation, and the low profitability of the agricultural sector. Currently, only 8.5% of the metropolitan region is devoted to agriculture, equivalent to around 16 square meters per inhabitant.

As artificial intelligence (AI) expands in education, schools are collecting more learning data than ever before. Yet increased measurement does not automatically produce deeper understanding. In a new study, Ruojun Zhong introduces a distributed learning architecture that integrates educational philosophy with AI-supported design. By embedding human judgment within feedback systems, the model aims to help education move from performance measurement toward continuous reflection and adaptive growth in the age of AI.