Naslov
Napredna i prediktivna poljoprivreda za otpornost klimatskim promjenama (AgroSPARC)
(Advanced and predictive agriculture for resilience to climate change (AgroSPARC))

Autori
Lemić, Darija ; Skendžić, Sandra ; Lešić, Vinko ; Orsag, Matko ; Pajač Živković, Ivana ; Zovko, Monika

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
Zbornik skupa / Krapac, Marin ; Goreta Ban, Smiljana - Poreč : Institut za poljoprivredu i turizam Poreč, 2020, 80-81

ISBN
978-953-7296-28-5

Skup
Znanstveni skup: Održivi razvoj poljoprivrede i turizma u kontekstu klimatskih promjena

Mjesto i datum
Poreč, Hrvatska, 12.11.2020

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Klimatske promjene, matematički modeli, umjetna inteligancija, predikcija
(Climate changes, mathematical models, artificial intelligence, prediction)

Sažetak
Current and future climate change is likely to have a significant impact on the cultivation of agricultural crops resulting in lower yields, higher costs and the necessary deviation from traditional cultivation. The aim of this project is to use artificial intelligence to develop mathematical models for different developmental stages of wheat and use these models to predict yields and plant growth. The analysis of a large datasets will be carried out in relation to different climatic conditions, which will be artificially generated and permuted in prototype chambers. These will then be correlated with identified indicators of plant development at different stages and different intensities of pest infestation. Artificial neural networks will then be developed that classify and select data on climatic conditions, weather forecasts and indicators of plant development. These neural networks will then learn and validate numerical models of different stages of plant development based on large experimental data sets. This activity involves determining the structure of the neural network and will take into account the available interdisciplinary and domain knowledge in agronomy. Neural network algorithms aim to run in real time using available short-term weather forecasting. The models will be used publicly and interactively via internet application to predict different stages of wheat development under real and hypothetical climatic conditions. In 2020, the European Regional Development Fund has supported the project "AgroSPARC- Advanced and predictive agriculture for resilience to climate change" is carried out by the Innovation Centre Nikola Tesla, the Faculty of Electrical Engineering and Computing and the Faculty of Agriculture at the University of Zagreb Croatia.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Poljoprivreda (agronomija)

POVEZANOST RADA