No abstract

No abstract

Understanding academic achievement (AA) is one of the most global challenges, as there is evidence that it is deeply intertwined with economic development, employment, and countries' wellbeing. However, the research conducted on this topic grounds in traditional (statistical) methods employed in survey (sample) data. This paper presents a novel approach, using state-of-the-art artificial intelligence (AI) techniques to predict the academic achievement of virtually every public high school student in Portugal, i.e., 110,627 students in the academic year of 2014/2015. Different AI and non-AI methods are developed and compared in terms of performance. Moreover, important insights to policymakers are addressed.

ABSTRACT1. Despite the ecological, environmental, and economic importance of mangroves, they are declining at an alarming rate worldwide, mostly as a result of human activities.2. Along the eastern African coast, Mozambique has the largest mangrove area. Fishing and farming are the main economic activities in the area, and people harvest mangrove vegetation for tannins, fuel wood, traditional medicine, boat-building, carpentry, and crafting.3. Landsat 5 TM imagery was used to map the distribution of trans-boundary mangrove areas along the Mtwara-Quirimbas Complex. Results for 1995 and 2005 are presented for the entire coastline and in more detail for the Ruvuma estuary, Quiterajo, Ibo/Quirimba islands, and Pemba Bay. Results were validated with a groundtruthing excursion in 2006, showing an overall thematic accuracy of 73%.4. Total estimated area of mangrove was 357 km 2 in 1995 and 368 km 2 in 2005, with the small net gain of 3% corresponding to a total gain of 32 km 2 and a total loss of 21 km 2 over this decade. 5. Results suggest that although Landsat TM imagery can be effective in mapping mangrove distribution, caution must be used in inferring its ecological condition.