Academy of Finland
Funding decision
 
Applicant / Contact person Raitoharju, Jenni
Organisation Finnish Environment Institute
Project title Advanced machine learning methods for biomonitoring
Decision No. 324475
Decision date 07.05.2019
Funding period 01.09.2019 - 31.08.2022
Funding 212 100
WebFOCUS Report
Project description
I propose developing machine learning algorithms to conquer challenges typically encountered automated image-based identification in biomonitoring. The considered challenges are i) unbalanced occurrence of different taxa, while most interesting taxa are rare, ii) variations in imaging conditions, which may harm identification accuracy, iii) detection of rare or invasive taxa that are absent in previously collected datasets, and iv) hierarchical nature of the identification task. I will apply state-of-the-art machine learning techniques and propose improvements to them to tackle the challenges. I will consider deep learning techniques such as Variational Auto-Encoders. The results can directly contribute to the environmental decision-making by speeding-up the biomonitoring process and resulting environmental mitigation measures as well as by allowing human experts to concentrate on both anomalies and higher-level implications of the monitoring results instead of routine identification.