Remote Sensing and Machine Learning in Crop Phenotyping and Management, with an Emphasis on Applications in Strawberry Farming

Measurement of plant characteristics is still the primary bottleneck in both breeding and crop management. Rapid accurate acquisition information about large populations critical for monitoring health dissecting underlying genetic traits. In recent years, high-throughput phenotyping technology has benefitted immensely from remote sensing machine learning. Simultaneous use multiple sensors (e.g., high-resolution RGB, multispectral, hyperspectral, chlorophyll fluorescence, light detection ranging (LiDAR)) allows a range spatial spectral resolutions depending on trait question. Meanwhile, computer vision learning methodology have emerged as powerful tools extracting useful biological image data. Together, these allow evaluation various morphological, structural, biophysical, biochemical this review, we focus development phenomics approaches strawberry farming, particularly those utilizing learning, with an eye toward future prospects strawberries precision agriculture. The research discussed broadly categorized according to traits related (1) fruit/flower detection, fruit maturity, quality, internal attributes, shape, yield prediction; (2) leaf canopy attributes; (3) water stress; (4) pest disease detection. Finally, present synthesis potential opportunities directions that could further promote farming.