Search

The knowledge of Sowing Dates (SD), Maximum Vegetative Development Dates (MVDD), and Harvest Dates (HD) of crops is important for estimating and forecasting large-scale productivity. Prior information on harvest date of crops is also useful in optimizing grain reception logistics and improving business decision-making in agro-industrial companies. This study aimed to develop a method to predict the HD of soybeans from MVDD, which was obtained from crop maps in the state of Paraná between 2011/2012 and 2013/2014 crop years. TIMESAT software was used to perform a seasonal trend analysis of enhanced vegetation index (EVI) time series from Moderate Resolution Imaging Spectroradiometer (MODIS) satellite imagery. After estimating time intervals between MVDD and HD (MH), applied to each mapped pixel, we calculated the 3 year MH average (average of the interval between MVDD and HD for the 3 crop years) for mesoregion and state levels, respectively. The MH by mesoregion was added to MVDD at a regional level, generating HDFORECAST, which is a prediction of the HD. Our results were compared with information from 44 monitored farms in the state in the 2013/2014 crop year. The findings showed that, for soybeans, MH by mesoregion can be used to predict HD with a Mean Error (ME) of 4.84 days, Mean Absolute Error (MAE) of 6.84 days, Root Mean Square Error (RMSE) of 8.12 days, Willmott modified coefficient (d) of 0.9, and Pearson correlation coefficient (r) of 0.88. Our study has produced valuable information for crop productivity models, as well as for logistics of grain transportation and storage in agro-companies, which can anticipate operations knowing when grains will be harvested and delivered to the centres. [ABSTRACT FROM AUTHOR]

Brazilian farming influences directly the worldwide economy. Thus, fast and reliable information on areas sown with the main crops is essential for planning logistics and public or private commodity market policies. Recent farming practices have embraced remote sensing to provide fast and reliable information on commodity dynamics. Medium-to-low resolution free orbital images, such as those from Landsat 8 and Sentinel 2, have been used for crop mapping; however, satellite image processing requires high computing power, especially when monitoring vast areas. Therefore, cloud data processing has been the only feasible option to deal with a large amount of orbital data and its processing and analysis. Thus, our goal was to develop a method to map the two main crops (soybeans and corn) in Paraná, one of the major Brazilian state producers. Landsat-8, Sentinel-2, SRTM+, and field data from 2016 to 2018 were used with the Simple Non-Iterative Clustering segmentation method and the Continuous Naive Bayes classifier, to identify cropped areas. A minimum global accuracy of 90% was found for both crops. Comparison with field data showed correlations of 0.96 and agreement coefficients no lower than 0.86. This ensures mapping quality when using Sentinel and/or Landsat imagery on the GEE platform. [ABSTRACT FROM AUTHOR]