Yield maps provide essential information to guide precision agriculture (PA) practices. Yet, on-board yield monitoring for sugarcane can be challenging. At the same time, orbital images have been widely used for indirect crop yield estimation for many crops like wheat, corn, and rice, but not for sugarcane. Due to this, the objective of this study is to explore the potential of multi-temporal imagery data as an alternative for sugarcane yield mapping. The study was based on developing predictive sugarcane yield models integrating time-series orbital imaging and a machine learning technique. A commercial sugarcane site was selected, and Sentinel-2 images were acquired from the beginning of the ratoon sprouting until harvesting of two consecutive cropping seasons. The predictive yield models RF (Random forest) and MLR (Multiple Linear Regression) were developed using orbital images and yield maps generated by a commercial sensor-system on harvesting. Original yield data were filtered and interpolated with the same spatial resolution of the orbital images. The entire dataset was divided into training and testing datasets. Spectral bands, especially the near-infrared at tillering crop stage showed greater contribution to predicting sugarcane yield than the use of derived spectral vegetation indices. The Root Mean Squared Error (RMSE) obtained for the RF regression based on multiple spectral bands was 4.63 Mg ha−1 with an R2 of 0.70 for the testing dataset. Overall, the RF regression had better performance than the MLR to predict sugarcane yield.
Aiming to evaluate the infrared thermography technique for early detection of subclinical mastitis in Gyrcows, 70 animals were selected in 2nd or 3rd lactation, with an average production of 7.2 kg / d between90 and 200 days in milking. Images of two quarters (front and backside) of the same udder side weremonthly performed during three months using a thermal camera to evaluate the surface temperature atthree different heights (upper, median and lower), totalizing 420 measurements. Milk samples fromeach quarter were also collected to evaluate the SCC and microbiological culture. The SCC did notinfluence udder temperature at different heights (p>0.05). However, temperatures among the regionsof the quarter were different, the upper area had higher values than the median and lower regions(p0.05). The use of thermal camera allowed the identification of temperature variationsof skin surface at different udder regions of Gyr cows. However, this technique was not effective in thedetection of subclinical mastitis.