Abstract
Pre-harvest yield estimation of mango fruit is important for the optimization of inputs and other resources on the farm. Current industry practice of visual counting the fruit on a small number of trees for yield forecasting can be highly inaccurate due to the spatial variability, especially if the trees selected do not represent the entire crop. Therefore, this study evaluated the potential of high resolution WorldView-3 (WV3) satellite imagery to estimate yield of mango by integrating both geometric (tree crown area) and optical (spectral vegetation indices) data using artificial neural network (ANN) model. WV3 images were acquired in 2016–2017 and 2017–2018 growing seasons at the early fruit stage from three orchards in Acacia Hills region, Northern Territory, Australia. Stratified sampling technique (SST) was applied to select 18 trees from each orchard and subsequently ground truthed for yield (kg·tree−1) and fruit number per tree. For each sampled tree, spectral reflectance data and tree crown area (TCA) was extracted from WV3 imagery. The TCA was identified as the most important predictor of both fruit yield (kg·tree−1) and fruit number, followed by NDVI red-edge band when all trees from three orchards in two growing seasons were combined. The results of all sampled trees from three orchards in two growing seasons using ANN model produced a strong correlation (R2 = 0.70 and 0.68 for total fruit yield (kg·tree−1) and fruit number respectively), which suggest that the model can be obtained to predict yield on a regional level. On orchard level also the ANN model produced a high correlation when both growing seasons were combined. However, the model developed in one season could not be applied in another season due to the influence of seasonal variation and canopy condition. Using the relationship derived from the measured yield parameters against combined VIs and TCA data, the total fruit yield (t·ha−1) and fruit number were estimated for each orchard, produced 7% under estimation to less than 1% over estimation. The accuracy of the findings showed the potential of WV3 imagery to better predict the yield parameters than the current practice across the mango industry as well as to quantify lost yield as a result of delayed harvest.
Highlights
Accurate pre-harvest yield estimation of high value fruit tree crops such as Mango (Mangifera indica) is of substantial benefit to industry as it allows growers to make more informed decisions on the optimizing of orchard inputs and to plan the logistics related with harvest, transport, marketing and forward selling
The panchromatic swaths were orthorectified using rational polynomial coefficients (RPCs) without XY control and the Shuttle Radar Topography Mission (SRTM) DEM resampled to 5m for Z control; tie points collected on the overlap regions; processing performed in PCI GXL using cubic convolution resampling
To develop regression models of total yield per tree and fruit number per tree with 18 VIs combined with tree crown area (TCA) data, artificial neural network (ANN) analysis was performed in R 3.5.0 statistical software [55]
Summary
Accurate pre-harvest yield estimation of high value fruit tree crops such as Mango (Mangifera indica) is of substantial benefit to industry as it allows growers to make more informed decisions on the optimizing of orchard inputs (e.g. irrigation water, fertilizers, pesticides etc.) and to plan the logistics related with harvest, transport, marketing and forward selling. Several sensor technologies including light detection and ranging (LiDAR), thermal imaging, ultrasonic sensors and machine vision systems were investigated for last several years to estimate fruits of individual trees for a number of different fruit crops, such as citrus [10,11,12], apples [13,14,15,16], grapes [17,18], almonds [19] and mangoes [1,2,20] In these studies, the focus lay mostly on the estimation of number of fruits, and not the overall yield (kg·ha−1) or the average fruit size (g) per tree, which are very important parameters for on farm management and harvest segregation. The trees receive 4–5 hours of water about 2 to 3 times per week in the dry season following flower initiation (approximately late April) through to fruit harvest (typically October)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
