To evaluate the accuracy of Discrete Wavelet Transform (DWT) in monitoring the chlorophyll (CHL) content of maize canopies based on RGB images, a field experiment was conducted in 2023. Images of maize canopies during the jointing, tasseling, and grouting stages were captured using unmanned aerial vehicle (UAV) remote sensing to extract color, texture, and wavelet features and to construct a color and texture feature dataset and a fusion of wavelet, color, and texture feature datasets. Backpropagation neural network (BP), Stacked Ensemble Learning (SEL), and Gradient Boosting Decision Tree (GBDT) models were employed to develop CHL monitoring models for the maize canopy. The performance of these models was evaluated by comparing their predictions with measured CHL data. The results indicate that the dataset integrating wavelet features achieved higher monitoring accuracy compared to the color and texture feature dataset. Specifically, for the integrated dataset, the BP model achieved an R2 value of 0.728, an RMSE of 3.911, and an NRMSE of 15.24%; the SEL model achieved an R2 value of 0.792, an RMSE of 3.319, and an NRMSE of 15.34%; and the GBDT model achieved an R2 value of 0.756, an RMSE of 3.730, and an NRMSE of 15.45%. Among these, the SEL model exhibited the highest monitoring accuracy. This study provides a fast and reliable method for monitoring maize growth in field conditions. Future research could incorporate cross-validation with hyperspectral and thermal infrared sensors to further enhance model reliability and expand its applicability.
Abstract The objective of this work was to establish and validate the dry matter distribution and yield prediction models based on physiological developmental timing, to compare the differences between the dry mass distribution index model and the dry mass distribution coefficient model, for the simulation of ear dry mass and to improve the accuracy of maize growth models for predicting yield. The experiments were conducted in three tropical sites (Longchuan, Mangshi, and Ruili) in the tropical region of Yunnan Province, China. The NRMS of ear dry mass and yield were generally less than 10. The dry mass distribution index method (NRMS = 5.44% and RMSE = 807.22 kg ha-1 for ear dry mass; and NRMS = 7.32% and RMSE = 707.67 kg ha-1 for grain yield) is better than the dry mass distribution coefficient method (NRMS = 7.52% and RMSE = 1115.31 kg ha-1 for ear dry mass; NRMS = 8.6% and RMSE = 830.76 kgha-1 for grain yield) to simulate maize ear dry mass and grain yield. The distribution index model improves the accuracy of the model, which is valuable for future maize production and management in Yunnan.
Garlic, as an important economic crop in China, still has room for improvement in terms of identification using remote sensing technology, Among them, high-precision classification of garlic has become an important subject. The Erhai Lake is an important freshwater lake in China. Under the influence of technology and policies, significant changes have occurred in the cultivation of garlic crops. this study constructed multidimensional features for crop classification suitable for Google Earth Engine, and Propose a method for identifying garlic crops using sample and feature datasets under limited conditions. The results indicate that: 1) In the land-use classification of the Erhai Lake Basin, the importance ranking of characteristic bands, from high to low, is as follows: spectral features, vegetation features, texture features, and terrain features. 2) The Random Forest method based on feature selection demonstrates high classification accuracy in land-use classification within the Erhai Lake Basin in Yunnan Province. The overall classification accuracy reaches 95.79%, with a Kappa coefficient of 0.9481. 3) The expansion direction of garlic cultivation in the Erhai Lake Basin initially strengthened and then weakened from 1999 to 2023. The vertical development of garlic cultivation reached saturation, showing a slow trend towards horizontal expansion between 2005 and 2018. The planting distribution in various townships in the Erhai Lake Basin gradually shifted from a relatively uniform distribution to an upstream development in the basin. This study utilizes the Google Earth Engine (GEE) cloud computing platform and machine learning algorithms to compensate for the lack of statistical data on garlic cultivation in the Erhai Lake Basin. Simultaneously, it accurately, rapidly, and efficiently extracts planting information, demonstrating significant potential for practical applications.
Dead heart of sugarcane is an important symptom caused by borer attack. In the present study, the spatial distribution and dynamics of dead heart of sugarcane in the field were investigated based on geostatistical analysis, and semivariograms were computed in four separate directions(0°, 45°, 90° and 135°) and fitted with various theoretical models to determine the best fitted one. The Ordinary Kriging was used to interpolate spatial data. The results revealed that the density of dead hearts of sugarcane increased in a single-peak pattern, and the degree of spatial aggregation and random variation both decreased with the increase in the density of dead heart. In addition, dead heart of sugarcane caused by borer exhibited spatial aggregation.With the increase in the density of dead heart, the degree of spatial aggregation decreased, while the correlation increased. Kriging interpolation indicated that the correlation between the spatial patches was weak in early seedling stage, and became strong in middle and late seedling stage.
Sugarcane bacilliform virus(SCBV) was detected by PCR from sugarcane showing chlorosis and mottle symptom from Kaiyuan,Yunnan Province.Part sequence of replicase gene of the isolate SCBV-Kaiyuan was determined.Sequence analysis indicated that the 589 bp of SCBV-Kaiyuan shared identities of 73.2%-74.0% and 83.1%-84.1% at nucleotide and amino acid levels with SCBV-Australia respectively,66.7%-68.4% and 65.6%-67.7% with SCBV-Morocco.The quality and yield of the sugarcane infected with SCBV-Kaiyuan was also investigated.The juice extraction,sucrose content,gravity purity and average stalk weight were decreased 1.55%,1.24%,2.22% and 0.26 kg in plants infected with SCBV-Kaiyuan,but reducing sugar was increased by 0.21% in infected plants.
In order to estimate the adaptability of Agricultural Production Systems Simulator (APSIM)-Maize model under the special climate environment in tropic, 10 field experiments were conducted at different seasons in three sites (Longchuan, Mangshi and Ruili) of tropic in Yunnan Province, China. The parameters of APSIM model were calibrated and its adaptability was validated. The results showed that the days from sowing to flowering and sowing to maturity were predicted accurately for all sites with mean errors of 2.0 ± 0.4, and 3.2 ± 0.7 d respectively. The normalized root mean square errors (NRMSE) of the model for yield prediction were 2%, 3% and 5% for each of three sites, respectively, which indicated that the APSIM model had good accuracy and sensitivity in predicting phenological phases and yield of maize (Zea mays L.) grown in different seasons, and the model had good adaptability in the tropic of Southwest China. This study provided the basis and technical support for evaluating maize production potential based on the model.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)