Citation: Walsh, K.B. In-Field Estimation of Fruit Quality and Quantity. Agronomy 2022, 12, 1074. https://doi.org/10.3390/ agronomy12051074 Received: 19 April 2022 Accepted: 25 April 2022 Published: 29 April 2022 Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affil- iations. Copyright: © 2022 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). agronomy Editorial In-Field Estimation of Fruit Quality and Quantity Kerry B. Walsh Institute for Future Farming Systems, Central Queensland University, Rockhampton, QLD 4701, Australia; k.walsh@cqu.edu.au Every new tool gives humankind a new capability or capabilities, as a new tool finds a range of applications. For example, the production of a magnifying lens allowed a new look at the natural world. Every generation of scientists since has accessed some new tool allowing a different view of the same subjects, from a compound microscope to a confocal microscope and beyond. Each new view enables new interpretations. This evolution also applies to agricultural applications. On a dairy farm, the pro- duction of every cow can now be monitored daily, and the herd can be managed at the level of the individual beast. In a wheat field, a satellite-acquired vegetation index map can be used for a variable-rate fertilizer application program. However, until now, fruit production has been based on a per-orchard basis rather than a per-tree basis. Technol- ogy advances, however, are throwing up a range of capabilities that allow for change in orchard management. Agriculturalists are both an inventive and adaptive lot. They are inventive in the sense that technology advances sometimes come from agricultural applications and are then applied elsewhere. For example, the field of near-infrared spectroscopy was pioneered in the 1960s context of an agricultural product quality control by Karl Norris of the United States Department of Agriculture. The technology soon flourished in other application areas and is heavily used today in a range of disciplines, from petrochemical to pharmaceutical, as well as agricultural industries such as diary, forage, and grain. Its use in the assessment of intact fruit, both on fruit pack lines and in the orchard, using handheld devices came later, beginning in the 1990s. However, agriculturalists are more commonly an adaptive lot, taking advantage of technologies developed for other applications, particularly from the medical, space, and defense sectors, given the well-funded R&D programs in those areas. Yield forecasts based on satellite- or drone-assessed vegetation indices are now commonplace for broadacre crops. Such technology-enabled forecasts of tree fruit harvest timing and load are yet to be widely commercially implemented, although advances in a range of technologies, including machine vision, image processing, LiDAR, and spectroscopy, hold promise for in-orchard assessment of various fruit crop attributes. The need to forecast tree fruit harvest timing and load has increased due to scale and distance factors. Scale refers to the increase in size of fruit production systems, with a time-poor orchard manager relying on forecasts in harvest resourcing decisions. Distance refers to the increasing length of global value chains, with the managerial need to forecast harvest timing and volume increasing with the complexity of the value chain. Relevant technologies used in the controlled environment of the packhouse are being shifted to use in the field environment of the orchard to address these needs. Examples include near-infrared spectroscopy (NIRS), used in assessment of fruit attributes relevant to the estimation of the optimum harvest timing, and machine vision techniques that allow for automated assessment of the flowering stage and level and fruit detection, sizing, and counting. These tools can inform farm management decisions on flower thinning, harvest timing, harvest resourcing (labour and materials), and marketing. Agronomy 2022, 12, 1074. https://doi.org/10.3390/agronomy12051074 https://www.mdpi.com/journal/agronomy