Potential of water balance and remote sensing-based evapotranspiration models to predict yields of spring barley and winter wheat in the Czech Republic

0545755 - ÚVGZ 2022 RIV NL eng J - Journal Article
Jurečka, František - Fischer, Milan - Hlavinka, Petr - Balek, Jan - Semerádová, Daniela - Bláhová, Monika - Anderson, M. C. - Hain, C. - Žalud, Zdeněk - Trnka, Miroslav
Potential of water balance and remote sensing-based evapotranspiration models to predict yields of spring barley and winter wheat in the Czech Republic.
Agricultural Water Management. Roč. 256, OCT (2021), č. článku 107064. ISSN 0378-3774. E-ISSN 1873-2283
R&D Projects: GA MŠMT(CZ) EF16_019/0000797
Research Infrastructure: CzeCOS III - 90123
Institutional support: RVO:86652079
Keywords : evaporative stress index * crop yield * agricultural drought * central-europe * united-states * time-series * soil * climate * system * parameterization * Artificial neural network * Crop yield prediction * Evapotranspiration * Evaporative stress index * Spring barley * Winter wheat
OECD category: Agriculture
Impact factor: 6.611, year: 2021
Method of publishing: Limited access
https://www.sciencedirect.com/science/article/pii/S0378377421003292?via%3Dihub

Indicators based on evapotranspiration (ET) provide useful information about surface water status, response of vegetation to drought stress, and potential growth limitations. The capability of ET-based indicators, including actual ET and the evaporative stress index (ESI), to predict crop yields of spring barley and winter wheat was analyzed for 33 districts of the Czech Republic. In this study, the ET-based indicators were computed using two different approaches: (i) a prognostic model, SoilClim, which computes the water balance based on ground weather observations and information about soil and land cover, (ii) the diagnostic Atmosphere-Land Exchange Inverse (ALEXI) model based primarily on remotely sensed land surface temperature data. The capability of both sets of indicators to predict yields of spring barley and winter wheat was tested using artificial neural networks (ANNs) applied to the adjusting number and timeframe of inputs during the growing season. Yield predictions based on ANNs were computed for both crops for all districts together, as well as for individual districts. The mot mean square error (RMSE) and coefficient of determination (R-2) between observed and predicted yields varied with date within the growing season and with the number of ANN inputs used for yield prediction. The period with the highest predictive capability started from early-June to mid-June. This optimal period for yield prediction was identifiable already at the lower number of ANN inputs, nevertheless, the accuracy of the prediction improved as more inputs were included within ANNs.The RMSE values for individual districts varied between 0.4 and 0.7 t ha(-1) while R-2 reached values of 0.5-0.8 during the optimal period. Results of the study demonstrated that ET-based indicators can be used for yield prediction in real time during the growing season and therefore have great potential for decision making at regional and district levels.
Permanent Link: http://hdl.handle.net/11104/0322417