Predicting the ripening time of avocado fruit accurately could improve fruit storage and decrease food waste. No reasonable method exists for predicting the postharvest ripening time of avocado fruit during transport, storage or retail display. Here, hyperspectral imaging ranging from 388 to 1005 nm with 462 bands was applied to 316 ‘Hass’ and 160 ‘Shepard’ mature, unripe avocado fruit to predict how many days it took for individual fruit to become ripe. Three models were developed using partial least squares regression (PLSR), deep convolutional neural network (DCNN) regression and DCNN classification. Our PLSR models provided coefficients of determination (R²) of 0.76 and 0.50 and root mean squared errors (RMSE) of 1.20 and 1.13 days for ‘Hass’ and ‘Shepard’ fruit, respectively. The DCNN-based regression models produced similar results with R² of 0.77 and 0.59, and RMSEs of 1.43 and 0.94 days for ‘Hass’ and ‘Shepard’ fruit, respectively. The prediction accuracies and RMSEs from DCNN classification models, respectively, were 67.28% and 1.52 days for ‘Hass’ and 64.06% and 1.03 days for ‘Shepard’. Our study demonstrates that the spectral reflectance of the skin of mature, unripe ‘Hass’ and ‘Shepard’ fruit provides adequate information to predict ripening time and, thus, has the potential to improve postharvest processing and reduce postharvest losses of avocado fruit.

准确预测鳄梨果实的成熟时间可以改善水果储存并减少食物浪费。没有合理的方法来预测鳄梨果实在运输、储存或零售展示过程中的采后成熟时间。在这里，对 316 个“Hass”和 160 个“Shepard”成熟、未成熟的鳄梨果实应用了 388 至 1005 nm 和 462 个波段的高光谱成像，以预测单个果实成熟所需的天数。使用偏最小二乘回归 (PLSR)、深度卷积神经网络 (DCNN) 回归和 DCNN 分类开发了三个模型。我们的 PLSR 模型提供了决定系数 (R ²) 的 0.76 和 0.50，以及 'Hass' 和 'Shepard' 果实的均方根误差 (RMSE) 分别为 1.20 天和 1.13 天。基于 DCNN 的回归模型产生了类似的结果，'Hass' 和 'Shepard' 果实的R ^{2分别为 0.77 和 0.59，RMSE 分别为 1.43 和 0.94 天。}DCNN 分类模型的预测准确度和 RMSE 分别为“Hass”的 67.28% 和 1.52 天，“Shepard”的预测准确度和 RMSE 分别为 64.06% 和 1.03 天。我们的研究表明，成熟、未成熟的“Hass”和“Shepard”果实表皮的光谱反射率提供了足够的信息来预测成熟时间，因此有可能改善鳄梨果实的采后加工并减少采后损失。