I am the AIMS-Carnegie junior research chair in data science, a resident researcher at AIMS, and  a senior lecturer in applied mathematics. I have a background in computer science (MSc) and applied mathematics (PhD). I discovered the wonderful world of machine learning and ecology during my fellowship where I obtained the Next Einstein AIMS-Canada fellowship in climate change science award. I lead the machine learning for eccology research group where I focus on passive acoustic monitoring of endangered species around the world.

It is during my PhD at Centre National de Recherche Scientifique (CNRS) in France that I discovered the world of deep learning while developing a model to automatically identify underwater behaviors of sea turtles from bio-loggers (animal-borne sensors). This experience ignited a passion within me to further enhance my expertise in deep learning, particularly in its application to conservation efforts. Currently, my research revolves around the creation of user-friendly tools based on deep learning techniques. The primary objective is to facilitate wildlife monitoring and streamline data processing in the field of ecology.

I'm a PhD student at the University of Lisbon. My bachelor's degree is in Environmental Biology with a minor in Statistics and Operational Research. My research focus on exploring AI methods to identify automatically animal vocalizations and other wildlife sounds.

My passion for machine learning started when I was studying at the University of Antananarivo in Madagascar. I have always been fascinated by how computers can understand and solve complex problems. My journey continued during my master structured program at AIMS, where I had the opportunity to explore the exciting intersection of machine learning and quantum computing through a unique project. Currently, I am working on machine learning for ecology, particularly to explore the development of real-time animal monitoring by leveraging the capabilities of compressed sensing to compress bioacoustic data. I joined ML4E driven by my love for nature and my passion for science and technology.

I'm a master's student in Biostatistics at Faculdade de Ciências da Universidade de Lisboa. Having a background in biology, I wanted to combine statistics and biology in my thesis. While participating on the ACCURATE project, I came into a challenge that inspired me to investigate the fascinating world of machine learning, which I now include into my research. Currently I’m focusing on evaluating passive acoustic data collected from beaked whales. This information was gathered with the use of DTAGs, which are devices attached to the whales to record underwater sounds. My thesis attempts to construct a model that automatically detects and classifies beaked whale vocalizations in order to speed up the research process.

I have an undergraduate degree in Mechatronic Engineering (currently working on a MSc in Applied Mathematics) and have always looked for a way to use technology in the aid of conservation and ecology. I believe that the fields of ecology and conservation have great potential for growth and are needed now more than ever before, especially within the African continent. Machine learning is an exciting and powerful tool that has so much potential to do lasting good in this realm, and I have been afforded the opportunity to be involved in that process. My research topic builds off the work of a previous student to perform posture estimation on the endangered African Penguin, adding in depth estimation and creating a more optimised model.

I have started to nurture a deep interest in machine learning long before I began my tertiary studies and always knew that I intended to pursue the field.  During my undergraduate degree in Industrial Engineering I took my first major step in dedicating myself towards that goal by doing my final year project in neural networks and population-based optimisation. Thereafter, I decided to embark on a postgraduate research degree in engineering. My research is centred around deep generative data augmentation strategies for limited data environments. In particular, scarce and endangered species for which data acquisition is challenging.