A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage

Nitrogen(N)and potassium(K)are two key mineral nutrient elements involved in rice growth.Accurate diagnosis of N and K status is very important for the rational application of fertilizers at a specific rice growth stage.Therefore,we propose a hybrid model for diagnosing rice nutrient levels at the early panicle initiation stage(EPIS),which combines a convolutional neural network(CNN)with an attention mechanism and a long short-term memory network(LSTM).The model was validated on a large set of sequential images collected by an unmanned aerial vehicle(UAV)from rice canopies at different growth stages during a two-year experiment.Compared with VGG16,AlexNet,GoogleNet,DenseNet,and inceptionV3,ResNet101 combined with LSTM obtained the highest average accuracy of 83.81%on the dataset of Huanghuazhan(HHZ,an indica cultivar).When tested on the datasets of HHZ and Xiushui 134(XS134,a japonica rice variety)in 2021,the ResNet101-LSTM model enhanced with the squeeze-and-excitation(SE)block achieved the highest accuracies of 85.38 and 88.38%,respectively.Through the cross-dataset method,the average accuracies on the HHZ and XS134 datasets tested in 2022 were 81.25 and 82.50%,respectively,showing a good generalization.Our proposed model works with the dynamic information of different rice growth stages and can efficiently diagnose different rice nutrient status levels at EPIS,which are helpful for making practical decisions regarding rational fertilization treatments at the panicle initiation stage.

Effects of increasing panicle-stage N on yield and N use efficiency of indica rice and its relationship with soil fertility

Because of the higher nitrogen(N)recovery efficiency(NRE)of panicle-stage fertilization compared with basal and tillering fertilization,increasing the proportion of N topdressing at the booting stage(panicleN)is recommended and commonly practiced in parts of China.To investigate the effects of increasing panicle-N on grain yield and N use efficiency(NUE)and the relationships of the increase and the rice cultivar and soil fertility status,we increased the percentage of panicle-N from 20%to 40%by correspondingly reducing the N amount applied only at the tillering stage in both high-and low-fertility blue clayey paddy fields in 2018 and 2019.Four indica cultivars with diverse panicle types were used,and their grain yield,dry matter accumulation,and NUE were compared.In high-fertility soil,increasing topdressing panicle-N from 20%to 40%reduced tillering ability and reduced the effective panicle numbers of the multi-and medium-panicle cultivars Huanghuazhan(HHZ),C Liangyouhuazhan(CHZ),and Tianyouhuazhan(THZ).These cultivars gave the greatest yield when 30%of N was supplied as panicle fertilizer,whereas the yield,NRE,N agronomic efficiency(NAE),and nitrogen physiological efficiency(NPE)of the heavy-panicle inbred cultivar Yangdao 6(YD6)continued to increase,resulting in improved dry matter accumulation and grain filling in the late growth stage.The yield,NAE,NRE,and NPE of YD6 peaked when the panicle-N constituted 40%.While in low-fertility soil,the multipanicle cultivar HHZ showed the greatest yield when 30%of fertilizer-N was applied once at the panicle initiation(PI)stage,while the medium-panicle cultivar CHZ showed the greatest yield when the panicle-N percentage was 40%.Our results suggest that the percentage of panicle-N fertilizer should not exceed 30%for multipanicle cultivars,while can be appropriately increased to 40%for heavy-panicle indica cultivars.The effect of increasing topdressing panicle-N on the yield of medium-panicle cultivars was related to soil fertility.The optimum panicle-N percentage was 30%in the high-fertility soil and 40%in the low-fertility soil.