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 sta...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.展开更多
Increasing levels of pollution within water bodies can cause eutrophication and an associated rapid growth in and reproduction of phytoplankton. Although most frequently occurring in bodies of water such as lakes and ...Increasing levels of pollution within water bodies can cause eutrophication and an associated rapid growth in and reproduction of phytoplankton. Although most frequently occurring in bodies of water such as lakes and dams, in recent years an increasing number of river systems in China have suffered serious algal blooms. The community structure of phytoplankton may differ, however, dependent on the hydrodynamic conditions and nutrient levels within the water body. The field investigation results obtained from a stagnant river in Suzhou City and Taihu Lake, China, showed that in water with higher concentrations of nitrogen and phosphorus, Chlorophyta became the predominant species and in water with lower concentrations of nitrogen and phosphorus, Cyanobacteria became the predominant species. Growth experiments with competitive species, Microcystis aeruginosa Kutz and Scenedesmus quadricauda （Turp.）, were conducted at three different nutrient levels. The biomass of algae in pure and mixed cultures was measured under conditions of different N/P ratios at oligotrophic, eutrophic and hypertrophic nutrient levels. The results indicated that the most suitable state for the growth and reproduction of M. aeruginosa and S. quadricauda were eutrophic conditions in both pure and mixed cultures. Under competition, however, the lower medium nutrient levels favoured M. aeruginosa, while the higher medium nutrient levels better suited S. quadricauda. Under similar hydrodynamic conditions, the community structure of phytoplankton in the water body was determined by the dominant species in competition for nutrients.展开更多
Caulerpa lentillifera is a green algae that distributes worldwide and is cultivated for food. We assessed vegetative propagation of C. lentillifera by measuring the specific growth rate （SGR） and chlorophyll fluores...Caulerpa lentillifera is a green algae that distributes worldwide and is cultivated for food. We assessed vegetative propagation of C. lentillifera by measuring the specific growth rate （SGR） and chlorophyll fluorescence of the green algae cultured at different salinities and nutrient levels. The results indicated that C. lentillifera can survive in salinities ranging from 20 to 50, and can develop at salinities of 30 to 40. The maximum SGR for C. lentillifera occurred at a salinity of 35. Both chlorophyll content and the ratio of variable to maximum fluorescence （F_v/F_m） were also at a maximum at a salinity of 35. Photosynthesis was inhibited in salinities greater than 45 and less than 25. Both the maximum SGR and maximum chlorophyll content were found in algae treated with a concentration of 0.5 mmol/L of NO3-N and 0.1 mmol/L of PO_4-P. The photosynthetic capacity of photosystem Ⅱ （PSⅡ） was inhibited in cultures of C. lentillifera at high nutrient levels. This occurred when NO_3-N concentrations were greater than 1.0 mmol/L and when PO4-P concentrations were at 0.4 mmol/L. As there is strong need for large-scale cultivation of C. lentillifera, these data contribute important information to ensure optimal results.展开更多
基金supported by the National Key Research and Development Program of China(2022YFD2300700)the Open Project Program of State Key Laboratory of Rice Biology,China National Rice Research Institute(20210403)the Zhejiang“Ten Thousand Talents”Plan Science and Technology Innovation Leading Talent Project,China(2020R52035)。
文摘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.
基金supported by the Natural Science Foundation of Jiangsu Province (No.BK2006710) the Hi-Tech Research and Development Program (863) of China (No:2003AA601100)
文摘Increasing levels of pollution within water bodies can cause eutrophication and an associated rapid growth in and reproduction of phytoplankton. Although most frequently occurring in bodies of water such as lakes and dams, in recent years an increasing number of river systems in China have suffered serious algal blooms. The community structure of phytoplankton may differ, however, dependent on the hydrodynamic conditions and nutrient levels within the water body. The field investigation results obtained from a stagnant river in Suzhou City and Taihu Lake, China, showed that in water with higher concentrations of nitrogen and phosphorus, Chlorophyta became the predominant species and in water with lower concentrations of nitrogen and phosphorus, Cyanobacteria became the predominant species. Growth experiments with competitive species, Microcystis aeruginosa Kutz and Scenedesmus quadricauda （Turp.）, were conducted at three different nutrient levels. The biomass of algae in pure and mixed cultures was measured under conditions of different N/P ratios at oligotrophic, eutrophic and hypertrophic nutrient levels. The results indicated that the most suitable state for the growth and reproduction of M. aeruginosa and S. quadricauda were eutrophic conditions in both pure and mixed cultures. Under competition, however, the lower medium nutrient levels favoured M. aeruginosa, while the higher medium nutrient levels better suited S. quadricauda. Under similar hydrodynamic conditions, the community structure of phytoplankton in the water body was determined by the dominant species in competition for nutrients.
基金Supported by the Technology Program of Basic Research of Qingdao(No.12-1-4-8-(2)-jch)
文摘Caulerpa lentillifera is a green algae that distributes worldwide and is cultivated for food. We assessed vegetative propagation of C. lentillifera by measuring the specific growth rate （SGR） and chlorophyll fluorescence of the green algae cultured at different salinities and nutrient levels. The results indicated that C. lentillifera can survive in salinities ranging from 20 to 50, and can develop at salinities of 30 to 40. The maximum SGR for C. lentillifera occurred at a salinity of 35. Both chlorophyll content and the ratio of variable to maximum fluorescence （F_v/F_m） were also at a maximum at a salinity of 35. Photosynthesis was inhibited in salinities greater than 45 and less than 25. Both the maximum SGR and maximum chlorophyll content were found in algae treated with a concentration of 0.5 mmol/L of NO3-N and 0.1 mmol/L of PO_4-P. The photosynthetic capacity of photosystem Ⅱ （PSⅡ） was inhibited in cultures of C. lentillifera at high nutrient levels. This occurred when NO_3-N concentrations were greater than 1.0 mmol/L and when PO4-P concentrations were at 0.4 mmol/L. As there is strong need for large-scale cultivation of C. lentillifera, these data contribute important information to ensure optimal results.
