Prediction of Harvest Time of Apple Trees: An RNN-Based Approach

Abstract

In the field of agricultural research, Machine Learning (ML) has been used to increase agricultural productivity and minimize its environmental impact, proving to be an essential technique to support decision making. Accurate harvest time prediction is a challenge for fruit production in a sustainable manner, which could eventually reduce food waste. Linear models have been used to estimate period duration; however, they present variability when used to estimate the chronological time of apple tree stages. This study proposes the PredHarv model, which is a machine learning model that uses Recurrent Neural Networks (RNN) to predict the start date of the apple harvest, given the weather conditions related to the temperature expected for the period. Predictions are made from the phenological phase of the beginning of flowering, using a multivariate approach, based on the time series of phenology and meteorological data. The computational model contributes to anticipating information about the harvest date, enabling the grower to better plan activities, avoiding costs, and consequently improving productivity. We developed a prototype of the model and performed experiments with real datasets from agricultural institutions. We evaluated the metrics, and the results obtained in evaluation scenarios demonstrate that the model is efficient, has good generalizability, and is capable of improving the accuracy of the prediction results.

A Crop Harvest Time Prediction Model for Better Sustainability, Integrating Feature Selection and Artificial Intelligence Methods

“…de Souza et al [6] proposed artificial neural networks (ANNs) for predicting banana harvest time. Furthermore, recurrent neural networks (RNNs) and convolutional neural networks (CNNs) have been adopted to predict crop harvest time [1,11]. However, ANNs and CNNs (more suitable for image data) cannot handle the pre-post relationship with the presentation of time series.…”

“…Making an accurate crop harvest time prediction is a challenge for sustainable agricultural management, but it could eventually decrease resource waste [1]. For harvest time prediction, previous studies have attempted to use statistical analyses to make predictions [2][3][4].…”

“…For harvest time prediction, previous studies have attempted to use statistical analyses to make predictions [2][3][4]. In recent years an increasing number of scholars have been utilizing artificial intelligence (AI) to solve the problem of harvest time prediction [1,5,6], and their results show that artificial intelligence methods are better than statistical methods [1]. For example, the long short-term memory (LSTM) model is used to construct a relationship between data by integrating data from different sources for machine learning (ML) [7,8].…”

RNN-Based Approach for Broccoli Harvest Time Forecast

“…While departing from traditional polynomial regression architectures, these models retained similar input features, such as temperature and solar radiation accumulation. For instance, LSTM networks were employed in [18] to improve apple production, exhibiting a three-day error in the average harvest day prediction. In a similar context, a study [19] demonstrated the estimation of bok choy production using advanced feature selection techniques to reduce the number of training parameters.…”

Effect of air temperature on each fruit growth and ripening stage of strawberry ‘Koiminori’

“…For example, an investigation into the relationship between temperature and fruit growth and the ripening stage of tomatoes revealed that the accelerating effect of temperature on fruit maturation varies with each stage (de Koning, 2000). Boechel et al (2022) also argued that predicting the harvest date of apples using a linear model with accumulated temperature as a variable is highly unreliable at specific stages and cannot adequately represent the phenomenon. Similar to tomatoes and apples, strawberries have different temperature sensitivities to maturity depending on the fruit growth and ripening stage; however, this has not been fully elucidated in previous studies.…”