Local-Scale Cereal Yield Forecasting in Italy: Lessons from Different Statistical Models and Spatial Aggregations
Statistical, data-driven methods are considered good alternatives to process-based models for the sub-national monitoring of cereal crop yields, since they can flexibly handle large datasets and can be calibrated simultaneously to different areas. Here, we assess the influence of several characteris...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/10/6/809 |
| _version_ | 1797565991858733056 |
|---|---|
| author | David García-León Raúl López-Lozano Andrea Toreti Matteo Zampieri |
| author_facet | David García-León Raúl López-Lozano Andrea Toreti Matteo Zampieri |
| author_sort | David García-León |
| collection | DOAJ |
| description | Statistical, data-driven methods are considered good alternatives to process-based models for the sub-national monitoring of cereal crop yields, since they can flexibly handle large datasets and can be calibrated simultaneously to different areas. Here, we assess the influence of several characteristics on the ability of these methods to forecast cereal yields at the local scale. We look at two diverse agro-climatic Italian regions and analyze the most relevant types of cereal crops produced (wheat, barley, maize and rice). Models of different complexity levels are built for all species by considering six meteorological and remote sensing indicators as candidate predictive variables. Yield data at three different spatial aggregation scales were retrieved from a comprehensive, farm-level dataset over the period 2001–2015. Overall, our results suggest the better predictability of summer crops compared to winter crops, irrespective of the model considered, reflecting a more intricate relationship among winter cereals, their physiology and weather patterns. At higher spatial resolutions, more sophisticated modelling techniques resting on feature selection from multiple indicators outperformed more parsimonious linear models. These gains, however, vanished as data were further aggregated spatially, with the predictive ability of all competing models converging at the agricultural district and province levels. Feature-selection models tended to elicit more satellite-based than meteorological indicators, with a preference for temperature indicators in summer crops, whereas variables describing the water content of the soil/plant were more often selected in winter crops. The selected features were, in general, equally distributed along the plant growing cycle. |
| first_indexed | 2024-03-10T19:20:30Z |
| format | Article |
| id | doaj.art-13eb677de35e434287a8e8bc7d90cbda |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-10T19:20:30Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-13eb677de35e434287a8e8bc7d90cbda2023-11-20T03:00:58ZengMDPI AGAgronomy2073-43952020-06-0110680910.3390/agronomy10060809Local-Scale Cereal Yield Forecasting in Italy: Lessons from Different Statistical Models and Spatial AggregationsDavid García-León0Raúl López-Lozano1Andrea Toreti2Matteo Zampieri3European Commission, Joint Research Centre (JRC), Edificio Expo, Inca Garcilaso 3, 41092 Seville, SpainINRAE, Avignon Université, UMR EMMAH, UMT CAPTE, 228 Route de l’Aérodrome–CS 40509, CEDEX 9, 84914 Avignon, FranceEuropean Commission, Joint Research Centre (JRC), Via Enrico Fermi 2749, I–21027 Ispra (VA), ItalyEuropean Commission, Joint Research Centre (JRC), Via Enrico Fermi 2749, I–21027 Ispra (VA), ItalyStatistical, data-driven methods are considered good alternatives to process-based models for the sub-national monitoring of cereal crop yields, since they can flexibly handle large datasets and can be calibrated simultaneously to different areas. Here, we assess the influence of several characteristics on the ability of these methods to forecast cereal yields at the local scale. We look at two diverse agro-climatic Italian regions and analyze the most relevant types of cereal crops produced (wheat, barley, maize and rice). Models of different complexity levels are built for all species by considering six meteorological and remote sensing indicators as candidate predictive variables. Yield data at three different spatial aggregation scales were retrieved from a comprehensive, farm-level dataset over the period 2001–2015. Overall, our results suggest the better predictability of summer crops compared to winter crops, irrespective of the model considered, reflecting a more intricate relationship among winter cereals, their physiology and weather patterns. At higher spatial resolutions, more sophisticated modelling techniques resting on feature selection from multiple indicators outperformed more parsimonious linear models. These gains, however, vanished as data were further aggregated spatially, with the predictive ability of all competing models converging at the agricultural district and province levels. Feature-selection models tended to elicit more satellite-based than meteorological indicators, with a preference for temperature indicators in summer crops, whereas variables describing the water content of the soil/plant were more often selected in winter crops. The selected features were, in general, equally distributed along the plant growing cycle.https://www.mdpi.com/2073-4395/10/6/809crop yield forecastingcerealsstatistical modelslassoridgeelastic net |
| spellingShingle | David García-León Raúl López-Lozano Andrea Toreti Matteo Zampieri Local-Scale Cereal Yield Forecasting in Italy: Lessons from Different Statistical Models and Spatial Aggregations Agronomy crop yield forecasting cereals statistical models lasso ridge elastic net |
| title | Local-Scale Cereal Yield Forecasting in Italy: Lessons from Different Statistical Models and Spatial Aggregations |
| title_full | Local-Scale Cereal Yield Forecasting in Italy: Lessons from Different Statistical Models and Spatial Aggregations |
| title_fullStr | Local-Scale Cereal Yield Forecasting in Italy: Lessons from Different Statistical Models and Spatial Aggregations |
| title_full_unstemmed | Local-Scale Cereal Yield Forecasting in Italy: Lessons from Different Statistical Models and Spatial Aggregations |
| title_short | Local-Scale Cereal Yield Forecasting in Italy: Lessons from Different Statistical Models and Spatial Aggregations |
| title_sort | local scale cereal yield forecasting in italy lessons from different statistical models and spatial aggregations |
| topic | crop yield forecasting cereals statistical models lasso ridge elastic net |
| url | https://www.mdpi.com/2073-4395/10/6/809 |
| work_keys_str_mv | AT davidgarcialeon localscalecerealyieldforecastinginitalylessonsfromdifferentstatisticalmodelsandspatialaggregations AT raullopezlozano localscalecerealyieldforecastinginitalylessonsfromdifferentstatisticalmodelsandspatialaggregations AT andreatoreti localscalecerealyieldforecastinginitalylessonsfromdifferentstatisticalmodelsandspatialaggregations AT matteozampieri localscalecerealyieldforecastinginitalylessonsfromdifferentstatisticalmodelsandspatialaggregations |