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 salinity and nutrients on the growth and chlorophyll fluorescence of Caulerpa lentillifera

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.

Effect of nutrient level on phytoplankton community structure in different water bodies

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.

Analysis of Nutrition of Total Mixed Ration for Dairy Cows on a Large-scale Ranch of Heilongjiang Reclamation Area

With the rapid development of China's dairy industry,the yield and scale of dairy cows have gradually increased,and the total mixed ration(TMR)technology has been widely applied in pastures.The seven large-scale pastures in the Heilongjiang reclamation area were selected.The area was divided into high milk yield pastures(A,E,F and G)and low milk yield pastures(B,C and D).The nutritional contents of TMR of the seven pastures were compared with NRC(2001)recommendations.The results showed that in the high milk yield pastures,the crude protein(CP)contents were closer to NRC recommendations(2001)than those of the low milk yield pastures,and the contents of ether extract(EE)were significantly higher(P<0.05).The contents of acid detergent fiber(ADF)in TMR of all the scale pastures were close to those recommended by NRC(2001),where as the contents of neutral detergent fiber(NDF)were significantly higher than the NRC(2001)recommendations.After measuring the dry matter(DM)rumen degradation rates,CP,NDF and ADF of TMR of dairy cows on the ranch were assessed using the nylon bag method,CP contents of the high milk yield pastures were significantly higher(P<0.05)compared with those of the low milk yield pastures,and the rumen degradable protein(RDP)to rumen undegradable protein(RUP)ratio was more ideal.The diets in the high milk yield pastures had significantly higher NDF contents and degradation rates than those in the low milk yield pastures,except pasture D(P<0.05).The diets in pastures E and G(with higher milk yields)had higher ADF degradation rates than pastures B,C and D,which had lower milk yields(P<0.05).Additionally,the type and digestibility of roughage were also related to dairy cows'performance.In summary,dairy cow performance was positively correlated with the nutrition of TMR.By exploring the quality of TMR from the aspects of TMR's nutritional contents,rumen degradation rates and feed ingredients,this study provided a reference for the evaluation of TMR nutrition.

Removal of Agricultural Non-Point Source Pollutants by Artificial Aquatic Food Web System: A Study Case of the Control of Cynobacterial Bloom in Jiyu River

An artificial aquatic food web (AAFW) system was designed to remove the non-point source pollutants in eutrophic Jiyu river. A certain amount of Scenedesmus obliquus and Daphnia pulex was cultured in the system for the control of serious cyanobacterial bloom. The AAFW system was a continuous-flow system including one storage basin of 3 m3 capacity with polluted river water (the total nitrogen-TN: 4.49 mg⋅l-1;the total phosphorus-TP: 0.192 mg⋅l-1), one phytoplankton tank of 3 m3 capacity with an initial concentrations of S. obliquus about 5.8 × 103 ind⋅l-1, and one zooplankton growth chamber of 1.5 m3 capacity with an initial abundance of D. pulex about 22.5 ind⋅l-1. The system was optimized by setting hydraulic retention time of phytoplankton tank as 5 days and the experiments were operated for 45 days. Compared with the polluted river, TN and TP were removed about 28% and 47% by the AAFW system, respectively. The biomass of phytoplankton decrease from 6.33 mg⋅l-1 to 1.48 mg⋅l-1 and the percentage of cyanobacteria decrease from 43.93% to 2.36%, the biomass of Crustacean zooplankton increase from 0.34 mg⋅l-1 to 1.53 mg⋅l-1 and the percentage of D. pulex increase from 19.19% to 57.62%. Our results indicated that the AAFW system not only is an efficient, flexible system for reducing nutrient levels in tributary rivers, but also has an ability to control the cyanobacteria bloom and rebuilding the aquatic ecosystem from the polluted river water.

Manipulation of SlMXl for enhanced carotenoids accumulation and drought resistance in tomato

Plants are the ultimate source of nutrients in the human diet. To ensure adequate availability of high quality food for an increasing world population, traits including improved tolerance of stresses and nutrient levels need to be selected in crops, both individually and in combination. Here we report the identification of SIMX1 encoding a MIXTA-like MYB transcription factor in tomato that simultaneously modulates drought resistance and metabolic processes through regulating key structural and regulatory genes of the corre- sponding pathways. Over-expression of SIMX1 results in substantially increased drought tolerance and improved fruit quality, while knocking down SIMX1 resulted in the opposite phenotypes. Our study indicates an effective way with multiplebeneficial traits by genetic engineering of a single regulatory gene and can be a novel approach to breeding crops.

Soil fungi of three native tree species inhibit biomass production and shift biomass allocation of invasive Mikania micrantha Kunth

Soil microbes contribute to native plant species successful resistance against invasive plant.Three native tree species,Heteropanax fragrans (HF),Cinnamomum burmanii (CB),and Macaranga tanarius (MT) were effective in controlling the notorious invasive vine Mikania micrantha (MM).Biomass production and allocation patterns (shoot/root biomass ratio (shoot/root)) are important indicators of MM climbing coverage and competitive light-capturing capacity.An investigation was conducted to test the role of soil microbes associated with the three native tree species to inhibit MM biomass production and shift MM shoot/root.Rhizosphere soils originating from preculture HF,CB,MT,and MM plots were collected separately for use as inocula.The inocula were mixed with sterilized river sand at a 1:9 (w/w) ratio to grow MM.The fungicide carbendazim (methyl benzimidazol-2-ylcarbamate) was applied to half the treatments to kill pathogenic soil fungi.Two nutrient levels were established based on the natural soil nutrient concentration from a field stand invaded by MM.MM were grown from seeds in a glasshouse,harvested 15 weeks after sowing,and separated into shoot and root portions.Results showed that under interaction of soil origin and nutrient levels,MM biomass production was unchanged,but biomass allocation patterns were significantly different.MM biomass production grown in the three native tree soils under two nutrient levels was similar or higher than MM biomass production in MM conspecific soil,indicating the absence of species-specific pathogens that inhibited MM biomass production in native tree soils.However,in both conspecific and tree soils,MM biomass production was significantly reduced in the presence of pathogenic soil fungi,i.e.MM experienced significant fungal inhibition,demonstrating the pathogenic soil fungi promoted native tree resistence to MM.MM exhibited decreased shoot biomass allocation when cultivated in native tree soil relative to MM conspecific soil under field stand nutrient level conditions.Reduced resource allocation to shoot biomass could result in diminished capacity to climb,cover,and subsequent smother to native trees,and reduced surface area exposed to available light.Following fungicide application,significant biomass allocation differences disappeared,suggesting the native tree soil fungi were responsible for decreasing MM shoot biomass.The overall results indicated tree soil fungi serve an integral role in controlling invasive MM through fungal inhibition on MM biomass production,and shifts in MM biomass allocation patterns.