Abstract
Food and feed production must be increased or maintained in order to meet the demands of the earth’s population. Under this scenario, the question that arises is how to address the demand for agricultural products given that the pressures on land use have already increased. In addition, it is obvious that climate change will have a serious negative impact and threaten the productivity and sustainability of food production systems. Therefore, understanding and predicting the outcome of crop production, while considering adaptation and sustainability, is essential. The need for information on decision making at all levels, from crop management to adaptation strategies, is constantly increasing and methods for providing such information are urgently needed in a relatively short period of time. Thus arises the need to use effective data, such as satellite and meteorological data, but also operational tools, to assess crop yields over local, regional, national, and global scales. In this work, three modeling approaches built on a fusion of satellite-derived vegetation indices, agro-meteorological indicators, and crop phenology are tested and evaluated in terms of data intensiveness for the prediction of wheat yields in large scale applications. The obtained results indicated that medium input data intensity methods are effective tools for yield assessments. The methods, namely, a semi-empirical regression model, a machine learning regression model, and a process-based model, provided high to moderate accuracies by fully relying on freely available datasets as sources of input data. The findings are comparable with those reported in the literature for detailed field experiments, thereby introducing a promising framework that can support operational platforms for dynamic yield forecasting, operating at the administrative or regional unit scale.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have