Citation: Dhonju, H.K.; Bhattarai, T.;
Amaral, M.H.; Matzner, M.; Walsh,
K.B. Management Information
Systems for Tree Fruit–2: Design of a
Mango Harvest Forecast Engine.
Horticulturae 2024, 10, 301. https://
doi.org/10.3390/horticulturae10030301
Academic Editors: Xinyang Yu and
Long Li
Received: 19 February 2024
Revised: 9 March 2024
Accepted: 19 March 2024
Published: 20 March 2024
Copyright: © 2024 by the authors.
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/).
horticulturae
Review
Management Information Systems for Tree Fruit–2: Design of a
Mango Harvest Forecast Engine
Hari Krishna Dhonju
1,
* , Thakur Bhattarai
1,2
, Marcelo H. Amaral
1
, Martina Matzner
1
and Kerry B. Walsh
1
1
Institute of Future Farming Systems, Central Queensland University, Rockhampton, QLD 4701, Australia;
t.bhattarai@cqu.edu.au (T.B.); m.m.amaral@cqumail.com (M.H.A.); k.walsh@cqu.edu.au (K.B.W.)
2
Thomas Elder Sustainable Agriculture, Elders P/L, Adelaide, SA 5000, Australia
* Correspondence: harikrishna.dhonju@cqumail.com; Tel.: +61-418-981-361
Abstract: Spatially enabled yield forecasting is a key component of farm Management Information
Systems (MISs) for broadacre grain production, enabling management decisions such as variable rate
fertilization. However, such a capability has been lacking for soft (fleshy)-tree-fruit harvest load, with
relevant tools for automated assessment having been developed only recently. Such tools include
improved estimates of the heat units required for fruit maturation and in-field machine vision for
flower and fruit count and fruit sizing. Feedback on the need for and issues in forecasting were
documented. A mango ‘harvest forecast engine’ was designed for the forecasting of harvest timing
and fruit load, to aid harvest management. Inputs include 15 min interval temperature data per
orchard block, weekly manual or machine-vision-derived estimates of flowering, and preharvest
manual or machine-vision-derived estimates of fruit load on an orchard block level across the farm.
Outputs include predicted optimal harvest time and fruit load, on a per block and per week basis,
to inform harvest scheduling. Use cases are provided, including forecast of the order of harvest of
blocks within the orchard, management of harvest windows to match harvesting resources such
as staff availability, and within block spatial allocation of resources, such as adequate placement of
harvest field bin and frost fans. Design requirements for an effective harvest MIS software artefact
incorporating the forecast engine are documented, including an integrated database supporting
spatial query, data analysis, processing and mapping, an integrated geospatial database for managing
of large spatial–temporal datasets, and use of dynamic web map services to enable rapid visualization
of large datasets.
Keywords: estimation; fruit load; geospatial database; orchard; planning; prediction
1. Introduction
1.1. Need for Harvest Forecast
Commercial orchards require management of irrigation, plant nutrition, disease and
pests, and tree canopy architecture to meet agronomic needs, and documentation of labor
and chemical usage to meet administrative requirements. As reviewed in a companion
paper [1], the development of electronic Management Information Systems (MISs) for
tree-fruit management lags behind that for broadacre cropping. The existing orchard
management systems have focused on issues with regulatory requirements, e.g., chemical
and labor usage, with capacities more recently developing around management decision
support, e.g., when to spray chemicals based on weather and pest pressures inputs.
Of the various management tasks involved in the production of soft tree fruit, the
annual organization of harvesting is a major event. Harvesting and grading costs represent
approximately 50% of total production costs for soft tree fruit [2], given the current need to
hand pick most commodities. Summarizing the review of [3], harvest forecast is essential
to the planning of on-farm resourcing (of labor and materials), transport and marketing,
with all of these areas having lead times of week if not months. Harvest forecasts are
Horticulturae 2024, 10, 301. https://doi.org/10.3390/horticulturae10030301 https://www.mdpi.com/journal/horticulturae