Vlatko Galic

Vlatko Galić is a data scientist with over five years significant experience in biometrics, data science, and machine learning. He earned his PhD in molecular biosciences with a focus on bioinformatics, genomics, and biometrics. Currently a Research Associate at the Agricultural Institute Osijek, Vlatko works with large-scale genomics, spectroscopy, and imaging data, applying predictive modeling to agricultural and climatological contexts. He is proficient in both R and Python, enjoys tackling messy datasets, and has contributed to several patents. He values continuous learning.

The speaker's profile picture

Sessions

04-08
18:10
60min
Dense temporal multispectral radiometry as a proxy for soil health assesment
Vlatko Galic

Transient soil properties are informative of many aspects of soil health. First, the directly measured properties such as drying rate and coloration changes can be informative of soil texture and mineral contents. Second, the changes in vegetation cover and the dynamics of biomass accumulation can serve as a proxy of the soil productivity and suitability for biomass production. Many of these traits can be readily retrieved from satellites, however, with limited temporal resolution. We developed a modular, low power IoT device combining multispectral radiometric capabilities (6 – 12 channels, 450 – 860nm) with simple weather station. The device harbors powerful industry-level SoC with onboard processing capability showing low power consumption, retrieving data in 15 minute intervals for two years on a single battery. During 2023 and 2024 five devices were set to maize crop fields for vegetation monitoring. The devices were positioned with GPS tracker to positions always covered by Sentinel 2-A tiles. Data analysis showed very strong correlations between proximally and remotely obtained vegetation indices. The usability of such data might be used during the cloudy days to support decision making processes. Moreover, the data can be interpolated to predict the regional dynamics during the cloudy weather. Such devices might also improve the monitoring capability of soil dynamics in forest vegetation where soil dynamics are not visible by optical sensing echnologies due to the tall vegetation cover. The usability of such devices will be discussed.

Let organizers decide
W - Invite