Area Estimation and Yield Forecasting of Wheat in Southeastern Turkey Using a Machine Learning Approach
- PDF / 1,155,503 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 32 Downloads / 228 Views
RESEARCH ARTICLE
Area Estimation and Yield Forecasting of Wheat in Southeastern Turkey Using a Machine Learning Approach O¨mer Vanli1
•
Ishfaq Ahmad2 • Burak Berk Ustundag3
Received: 11 November 2019 / Accepted: 1 October 2020 Ó Indian Society of Remote Sensing 2020
Abstract Accurate and timely information on yield forecasting is necessary for policymakers in decision-making. The case study was planned to develop a framework for the regional wheat yield forecasting model for southeastern Turkey. Therefore, after implementing Top of Atmospheric (TOA) correction for all images and collecting ground-truthing point of 313 fields from the Nurdagi and Islahiye counties. A total of eight machine learning algorithms were tuned and tested for the satellite image classification so that best model was used for the spatial distribution of wheat crop. The results of machine learning algorithms showed an accuracy greater than 90%. As the best model, the random forest was used for image classification. The classification results showed that area estimated by the classifier were 11% more than those reported by the Turkish statistical department. The observed and predicted yield of the tested model was closed to each other with root mean square error (RMSE) of 198 kg ha-1. The observed and predicted yield showed a close agreement with RMSE of 144 kg ha-1 at Nurdagi and 68 kg ha-1 at Islahiye for 5 years. It is concluded that remote sensing is useful tools for estimation of yield and developed can be used for other regions and crops. Keywords Machine learning algorithms LASSO analysis Yield forecasting Area estimation
Introduction Accurate yield forecasting is becoming an essential requirement for the policymakers in decision-making. Previous approaches have proven to be inadequate; the purpose of this study is to develop an improved method of regional wheat yield estimation. Wheat is an important crop in Turkey due to its nutritious and economic value. The total cultivated area of ¨ mer Vanli & O [email protected] Ishfaq Ahmad [email protected] Burak Berk Ustundag [email protected] 1
Department of Geographical Information Technologies, Istanbul Technical University, Istanbul, Turkey
2
Centre for Climate Research and Development, COMSATS University Islamabad, Islamabad, Pakistan
3
Informatics Institute, Istanbul Technical University, Istanbul, Turkey
winter wheat in Turkey was 6.43 million hectares (Turkish Statistical Institute 2017). To meet the demand of the everincreasing population of Turkey, there is dire need to sustain the productivity of wheat (Nevo et al. 2013). Timely and accurate information on the wheat estimates will be very useful for policymakers in import and export decisions (Das and Singh 2013; Dempewolf et al. 2014; Fahad et al. 2019; Saeed et al. 2017). Conventional methods used for yield estimation are time-consuming and labor-intensive, and the samples collected from a few villages are not true representative of the populations (Hamzacebi and Es 2014). For this purpose, remote sens
Data Loading...
