Welcome / Research output / Articles / Articles published in other peer-review journals / An Approach Using Entropy and Supervised Classifications to Disaggregate Agricultural Data at a Local Level

An Approach Using Entropy and Supervised Classifications to Disaggregate Agricultural Data at a Local Level

Xavier, A., Fragoso, R., Costa Freitas, M., Rosário, M. (2019), "An Approach Using Entropy and Supervised Classifications to Disaggregate Agricultural Data at a Local Level", Journal of Quantitative Economics, 17, 763-779.
Abstract:

Changes in the Common Agricultural Policy (CAP) had several consequences on land-use and on the environment. This calls for detailed disaggregated agricultural data with precise geographical references. To tackle such problems data disaggregation processes are needed and a series of studies are being carried out at international level, which still have not taken the utmost advantage of remote sensing technologies by combining them with mathematical programming methods, namely entropy. Therefore, the objective of this article was to provide an approach to disaggregate agricultural data at the local level, taking advantage of the existent up-to-date satellite imagery and an entropy approach for manage different sets of data. The results were compared with other approaches and showed to be coherent, and may be improved further with the inclusion of other information.