LASIGE’s PhD student João Batista is presenting his research work in the first PhD in Informatics Seminar of 2019/2020, on this Thursday, April 30 at 12h.
The PhD in Informatics Seminars are open to PhD students, faculty, MSc and BSc students and are an excellent opportunity for cross-disciplinary development through presentation and discussion of edge research going on in Ciências ULisboa Departments of Informatics.
Title: Evolving Generalist and Interpretable Land Cover Models for Forest Monitoring
Speaker: João Batista (LASIGE/DI)
When: April 30 (Thursday) at 12:00
Where: Zoom videoconference (for more information access: https://moodle.ciencias.ulisboa.pt/course/view.php?id=2228)
Deforestation has serious implications on biodiversity, on rural communities that are dependent on forests for food and income, and on greenhouse gas emissions that are driving the global climate. One way to control deforestation is through the use of mechanisms that promote sustainable forestry and support economic development. However, these mechanisms require careful forest monitorization to be effective.
This monitorization can be made using Remote Sensing techniques. In this work, we used satellite images. Although this has been done for some decades, problems still exist, such as the noise inside each image which is intensified across different images, making the creation of general machine learning models a non-trivial task.
In my PhD research, I am currently studying the application of Genetic Programming algorithms in the creation of new hyper-features that are both easily interpretable and able to create models that are general enough to be used in multiple satellite images without the need for an expert to change the parameters for every new image.