Investigating forest phenology prediction is a key parameter for assessing the relationship between climate and environmental changes. Traditional machine learning models are not good at capturing long-term dependencies due to the problem of vanishing gradients. In contrast, the Gated Recurrent Unit (GRU) can effectively address the problem of vanishing gradients and allow the neural network to capture longer-range dependencies. In this study, an optical camera was used as experimental equipment to obtain forest images. The absolute greenness index (GEI) data of the region of interest (ROI) in the images were calculated to fit the seasonal variation curve of forest phenology. The GRU neural network model was introduced to train and analyze the GEI data, and the performance of the GRU neural network was evaluated using the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) methods. Finally, the model was used to predict the trend of GEI data for the next 60 days. The results showed that: (1) In terms of training and predicting forest phenology, the GRU model was validated using histograms and autocorrelation graphs, which indicated that the distribution of predicted data was consistent with the trend of actual data, the GRU model data was feasible, and the model was stable. (2) The MSE values of the GRU model at rain-fed-CK (preset point 1), sufficient drip irrigation-DIFI (preset point 3), and sufficient furrow irrigation-BIFI (preset point 5) were 9.055 × 10⁻⁵, 12.91 × 10⁻⁵, and 8.241 × 10⁻⁵, respectively. The RMSE values were 9.516 × 10⁻³, 11.36 × 10⁻³, and 7.313 × 10⁻³, respectively. The MAE values were 7.174 × 10⁻³, 8.241 × 10⁻³, and 5.351 × 10⁻³, respectively. These results indicate that the overall performance of the GRU model was good. (3) The predicted GEI data for the next 60 days showed a trend consistent with actual changes in GEI data, as demonstrated by the GRU model. The GRU model has become the preferred method for phenological prediction due to its simple internal structure and relatively short training time. Results show that the GRU model can achieve forest phenological change prediction and can reveal in-depth insights into future forest growth and climate change, providing a theoretical basis for the application of forest phenological prediction.

Due to global warming, changes in plant phenology such as an early leaf spreading period in spring, a late abscission period in autumn, and growing season extension are commonly seen. Here, near-earth remote sensing images were used to monitor the canopy phenology of Populus tomentosa B301 in planted forests under full drip irrigation, full furrow irrigation, and no irrigation (rain fed). Experiments were conducted to collect phenological data across a growing season. Continuous canopy images were used to calculate different vegetation indices; the key phenological period was determined via the double logistic model and the curvature method. The effects of irrigation methods and precipitation in the rainy season on tree growth changes and key phenological periods were analyzed. The results showed that: (1) The green chromatic coordinate (GCC) conformed to the vegetation index of the tree species canopy phenological study. (2) During the phenological period throughout the year, the GCC reaching peak time (MOE) of the canopy phenology of Populus tomentosa B301 was the same in the three methods, while the time of shedding at the end of the growing season without irrigation (preset point 1) was 8 days longer than with full drip irrigation (preset point 3), and 7 days faster than with full furrow irrigation (preset point 5). (3) In the preliminary rainy season, different irrigation volumes induced different growth changes and phenological periods of the trees, resulting in different data of vegetation indicators under different growth conditions. (4) During the rainy season, the precipitation had different effects on cultivating P. tomentosa B301 using the three methods, that is, high precipitation could increase the growth rate of the fully irrigated area, otherwise the growth rate of this tree species was increased in full drip irrigation areas. Precipitation was lower and irregular, and the growth rate of this species was faster than the other two irrigation methods in the non-irrigated area, which was more adaptable to external environmental changes. The internal growth mechanism of the phenological changes in different areas of the planted forests was influenced by the different cultivation methods. Moreover, the collected phenological data provide a basis for the study of plant phenology with large data sets and deepens our understanding of the phenology of planted forests in response to climate change.