Most rice growth stage predictions are currently based on a few rice varieties for prediction method studies, primarily using linear regression, machine learning, and other methods to build growth stage prediction models that tend to have poor generalization ability, low accuracy, and face various challenges. In this study, multispectral images of rice at various growth stages were captured using an unmanned aerial vehicle, and single-plant rice silhouettes were identified for 327 rice varieties by establishing a deep-learning algorithm. A growth stage prediction method was established for the 327 rice varieties based on the normalized vegetation index combined with cubic polynomial regression equations to simulate their growth changes, and it was first proposed that the growth stages of different rice varieties were inferred by analyzing the normalized difference vegetation index growth rate. Overall, the single-plant rice contour recognition model showed good contour recognition ability for different rice varieties, with most of the prediction accuracies in the range of 0.75–0.93. The accuracy of the rice growth stage prediction model in recognizing different rice varieties also showed some variation, with the root mean square error between 0.506 and 3.373 days, the relative root mean square error between 2.555% and 14.660%, the Bias between1.126 and 2.358 days, and the relative Bias between 0.787% and 9.397%; therefore, the growth stage prediction model of rice varieties can be used to effectively improve the prediction accuracy of the growth stage periods of rice.

Areca palm (Areca catechu L.) is an important perennial tropical cash crop in Hainan Province, and accurate information on its spatial distribution is essential for plantation monitoring and land-resource management. Focusing on Sanya, China, this study integrated 0.59 m RGB imagery acquired from Google Earth between October 2021 and February 2025, field surveys conducted in 2025, Landsat time-series data from 1986 to 2016, ASTER GDEM V3 data, and data from the 2019 Third National Land Survey. Three ResNet U-Net models were compared with Segment Anything Model adapted using Low-Rank Adaptation (SAMLoRA) using a ViT-B backbone, and the mapped distribution was further analyzed in terms of spatial clustering, terrain characteristics, historical spectral changes, and land-use context. SAMLoRA demonstrated favorable segmentation performance and was selected for citywide mapping. After manual cross-checking, the estimated area of areca palm plantations was 5468 ha, with most plantations concentrated in Tianya and Yazhou districts. Spatial analysis revealed significant clustering, and plantations occurred predominantly on gentle slopes. Historical spectral and land-use analyses further indicated that most mapped plantations showed no candidate spectral disturbance under the specified parameters and corresponded primarily to the “other garden land” category. This study provides a city-scale, high-resolution distribution baseline for fragmented tropical cash-crop plantations and offers a practical framework for plantation monitoring, agricultural spatial planning, and future assessments of land-use transitions and environmental suitability.