Mathematical modeling has been used to describe the characteristics of crop growth. Establishing a growth model can help to better understand the responses of crops to their environment and improve the efficiency of agricultural production. This study establishes empirical growth models to predict the growth of greenhouse tomato. In this study, we collected beef tomato (Solanum lycopersicum cv. ‘993′) growth data over two crop seasons in Taiwan and established growth models by employing the commonly used Gompertz and Logistic curves. Days after transplanting (DAT) and growing degree-days (GDD) were introduced as independent variables and their relationships with five traits, i.e., plant height, leaf area index, stem dry matter, leaves dry matter, and fruits dry matter were determined. The performances of GDD models were slightly better than those of the DAT models. In addition, we inferred five critical points with biological meaning based on the proposed growth models. The critical points estimated by the Logistic model are closer to our expectation than those of the Gompertz model, and they were applicable for the ‘993′ tomato in Taiwan. These results can be used to predict tomato growth and adjust the fieldwork schedule to improve the efficiency of the greenhouse production of tomatoes.

In subtropical regions, tomato (Solanum lycopersicum) is mainly produced in autumn and winter. To enhance the off-season production of tomato, summer cultivation has become a prime objective. Grafting tomato scions onto eggplant (Solanum melongena) rootstocks is a key method to overcome the difficulties of tomato cultivation in summer. In this study, we collected seedling growth data over six growing seasons in Taiwan and established growth models by employing three commonly used sigmoid growth curves, namely the Gompertz, Richards, and Logistic curves. Cumulative temperature was introduced as an independent variable and its relationship with plant stem diameter determined. The R² values of the growth models were 0.74–0.85 and 0.72–0.80 in calibration and validation, respectively. Performance did not differ markedly among models in the same growing season, but notable differences were observed among models for different growing seasons. In addition, the estimates of several model parameters differed significantly among the seasons; hence, separate models should be established for different seasons. The results of this study can be used in prediction of tomato and eggplant seedling growth and arrangement of the grafting schedule to improve the efficiency of seedling production in subtropical countries.

Detection of the early stages of stress is crucial in stabilizing crop yields and agricultural production. The aim of this study was to construct a nondestructive and robust method to predict the early physiological drought status of the tomato (Solanum lycopersicum); for this purpose, a convolutional neural network (CNN)-based model with a one-dimensional (1D) kernel for fitting the visible and near infrared (Vis/NIR) spectral data was proposed. To prevent degradation and enhance the feature comprehension of the deep neural network architecture, residual and global context modules were embedded in the proposed 1D-CNN model, yielding the 1D spectrogram power net (1D-SP-Net). The 1D-SP-Net outperformed the 1D-CNN, partial least squares discriminant analysis (PLSDA), and random forest (RF) models in model testing, demonstrating an accuracy of 96.3%, precision of 98.0%, Matthew’s correlation coefficient of 0.92, and an F1 score of 0.95. Furthermore, when employing various synthesized imbalanced data sets, the proposed 1D-SP-Net remained robust and consistent, outperforming the other models in terms of the prediction capabilities. These results indicate that the 1D-SP-Net is a promising model resistant to the effects of imbalanced data sets and able to determine the early drought stress status of tomato seedlings in a non-invasive manner.

Compared with open-field cultivation, greenhouses can provide favorable conditions for crops to grow through environmental control. The prediction of greenhouse microclimates is a way to reduce environmental monitoring costs. This study used several recurrent neural network models, including long short-term memory (LSTM), gated recurrent unit, and bi-directional LSTM, with varying numbers of hidden layers and units, to establish a temperature forecasting model for a plastic greenhouse. To assess the generalizability of the proposed model, the most accurate forecasting model was used to predict the temperature in a greenhouse with different specifications. During a test period of four months, the best proposed model’s R², MAPE, and RMSE values were 0.962, 3.216%, and 1.196 °C, respectively. Subsequently, the outputs of the temperature forecasting model were used to calculate growing degree days (GDDs), and the predicted GDDs were used as an input variable for the sigmoid growth models to simulate the leaf area index, fresh fruit weight, and aboveground dry matter of tomatoes. The R² values of the growth model for the three growth traits were all higher than 0.80. Moreover, the fitted values and the parameter estimates of the growth models were similar, irrespective of whether the observed GDD (calculated using the actual observed data) or the predicted GDD (calculated using the temperature forecasting model output) was used. These results indicated that the proposed temperature forecasting model could accurately predict the temperature changes inside a greenhouse and could subsequently be used for the growth prediction of greenhouse tomatoes.

The reference evapotranspiration (ET₀) information is crucial for irrigation planning and water resource management. While the Penman-Monteith (PM) equation is widely recognized for ET₀ calculation, its reliance on numerous meteorological parameters constrains its practical application. This study used 28 years of meteorological data from 18 stations in four geographic regions of Taiwan to evaluate the effectiveness of an artificial intelligence (AI) model for estimating PM-calculated ET₀ using limited meteorological variables as input and compared it with traditional methods. The AI models were also employed for short-term ET₀ forecasting with limited meteorological variables. The findings suggested that AI models performed better than their counterpart methods for ET₀ estimation. The artificial neural network using temperature, solar radiation, and relative humidity as input variables performed best, with the correlation coefficient (r) ranging from 0.992 to 0.998, mean absolute error (MAE) ranging from 0.07 to 0.16 mm/day, and root mean square error (RMSE) ranging from 0.12 to 0.25 mm/day. For short-term ET₀ forecasting, the long short-term memory model using temperature, solar radiation, and relative humidity as input variables was the best structure to forecast four-day-ahead ET₀, with the r ranging from 0.608 to 0.756, MAE ranging from 1.05 to 1.28 mm/day, and RMSE ranging from 1.35 to 1.62 mm/day. The percentage error of this structure was within $\pm$5% for most meteorological stations over the one-year test period, underscoring the potential of the proposed models to deliver daily ET₀ forecasts with acceptable accuracy. Finally, the proposed estimating and forecasting models were developed in regional and variable-limited scenarios, making them highly advantageous for practical applications.