Integrating field images and microclimate data to realize multi-day ahead forecasting of maize crop coverage using CNN-LSTM

Crop coverage(CC)is an important parameter to represent crop growth characteristics,and the ahead forecasting of CC is helpful to track crop growth trends and guide agricultural management decisions.In this study,a novel CNN-LSTM model that combined the advantages of convolutional neural network(CNN)in feature extraction and long short-term memory(LSTM)in time series processing was proposed for multi-day ahead forecasting of maize CC.Considering the influence of climate change on maize growth,five microclimatic factors were combined with historical maize CC estimated from field images as the input variables of the forecasting model.The field experimental data of four observation points for more than three years were used to evaluate the performance of CNN-LSTM at the forecasting horizon of three to seven days ahead and compared the forecasting results to CNN and LSTM.The results demonstrated that CNN-LSTM obtained the lowest RMSE and the highest R2 at all forecasting horizons.Subsequently,the performance of CNN-LSTM under univariate(historical maize CC)and multivariate(historical maize CC+microclimatic factors)input was compared,and the results indicated that additional microclimatic factors were effective in improving the forecasting performance.Furthermore,the 3-day ahead forecasting results of CNN-LSTM in different growth stages of maize were also analyzed,and the results showed that the highest forecasting accuracy was obtained in the seven leaves stage.Therefore,CNN-LSTM can be considered a useful tool to forecast maize CC.

Significant reduction of ammonia emissions while increasing crop yields using the 4R nutrient stewardship in an intensive cropping system

Ammonia (NH_3) emissions should be mitigated to improve environmental quality.Croplands are one of the largest NH_3sources,they must be managed properly to reduce their emissions while achieving the target yields.Herein,we report the NH_3 emissions,crop yield and changes in soil fertility in a long-term trial with various fertilization regimes,to explore whether NH_3 emissions can be significantly reduced using the 4R nutrient stewardship (4Rs),and its interaction with the organic amendments (i.e.,manure and straw) in a wheat–maize rotation.Implementing the 4Rs significantly reduced NH_3 emissions to 6 kg N ha~(–1) yr~(–1) and the emission factor to 1.72%,without compromising grain yield (12.37 Mg ha~(–1) yr~(–1))and soil fertility (soil organic carbon of 7.58 g kg~(–1)) compared to the conventional chemical N management.When using the 4R plus manure,NH_3 emissions (7 kg N ha~(–1) yr~(–1)) and the emission factor (1.74%) were as low as 4Rs,and grain yield and soil organic carbon increased to 14.79 Mg ha~(–1) yr~(–1) and 10.09 g kg~(–1),respectively.Partial manure substitution not only significantly reduced NH_3 emissions but also increased crop yields and improved soil fertility,compared to conventional chemical N management.Straw return exerted a minor effect on NH_3 emissions.These results highlight that 4R plus manure,which couples nitrogen and carbon management can help achieve both high yields and low environmental costs.

Application of Nejayote as a Foliar and Edaphic Fertiliser to Native Blue Maize (Zea mays L.) Crops

Raw and treated “nejayote” were assessed as foliar and edaphic fertilisers for native blue maize (Zea mays L.) crops in the municipality of Amozoc de Mota, Puebla, Mexico, during the 2015 agricultural cycle. Treated nejayote refers to raw nejayote subjected to a coagulation-flocculation process. Two states of nejayote were established (raw and treated nejayote) with different physicochemical properties. Foliar bio-fertilisers were prepared from raw and treated nejayote and mixed with organic matter (OM) to promote a fermentation process. The foliar treatments used were: BNC5, BNC15, BNC30 (raw nejayote-based bio-fertiliser at 5%, 15%, and 30%), BNCQ5, and NCQ30 (nejayote treated by chemical coagulation at 5% and 30%), with BT as a control (traditional bio-fertiliser). The edaphic treatments used were: NC50, NC75, and NC100 (raw nejayote at 50%, 75%, 100%), with AP as a control (drinking water), thus giving rise to 10 treatments in terms of content of raw or treated nejayote. Foliar and edaphic field treatments applied to native blue maize crops were statistically assessed using the following response variables: plant height, stem diameter, number of leaves, and grain yield. The experiment was laid out in a randomised complete block design (RCBD) with five replications of each treatment. The results obtained showed, that foliar or edaphic application at the different stages of development did not produce statistically significant differences, at P ≤ 0.05, in terms of response variables. The most significant effects occurred at the early stage of plant development and were mainly reflected in the stem diameter with foliar treatment NCQ30 and in the number of leaves with foliar treatment BNC5. At the final stage of crop development, the highest yield (0.639 ± 0.121 t·ha-1) was obtained with treatment BNC5, which produced a statistically significant difference (b) in relation to the rest of the foliar and edaphic treatments (Tukey P ≤ 0.05).

InstaCropNet:An efficient Unet-Based architecture for precise crop row detection in agricultural applications

Autonomous navigation in farmlands is one of the key technologies for achieving autonomous management in maize fields.Among various navigation techniques,visual navigation using widely available RGB images is a cost-effective solution.However,current mainstream methods for maize crop row detection often rely on highly specialized,manually devised heuristic rules,limiting the scalability of these methods.To simplify the solution and enhance its universality,we propose an innovative crop row annotation strategy.This strategy,by simulating the strip-like structure of the crop row's central area,effectively avoids interference from lateral growth of crop leaves.Based on this,we developed a deep learning network with a dual-branch architecture,InstaCropNet,which achieves end-to-end segmentation of crop row instances.Subsequently,through the row anchor segmen-tation technique,we accurately locate the positions of different crop row instances and perform line fitting.Experimental results demonstrate that our method has an average angular deviation of no more than 2°,and the accuracy of crop row detection reaches 96.5%.

Field scale interaction and nutrient exchange between surface water and shallow groundwater in the Baiyang Lake region,North China Plain

Fertilizer input for agricultural food production, as well as the discharge of domestic and industrial water pollutants, increases pressures on locally scarce and vulnerable water resources in the North China Plain. In order to：（a） understand pollutant exchange between surface water and groundwater,（b） quantify nutrient loadings, and（c） identify major nutrient removal pathways by using qualitative and quantitative methods, including the geochemical model PHREEQC） a one-year study at a wheat（Triticum aestivum L.） and maize（Zea mays L.） double cropping system in the Baiyang Lake area in Hebei Province, China, was undertaken. The study showed a high influence of low-quality surface water on the shallow aquifer. Major inflowing pollutants into the aquifer were ammonium and nitrate via inflow from the adjacent Fu River（up to 29.8 mg/L NH4-N and 6.8 mg/L NO3-N）, as well as nitrate via vertical transport from the field surface（up to 134.8 mg/L NO3-N in soil water）. Results from a conceptual model show an excess nitrogen input of about 320 kg/ha/a. Nevertheless,both nitrogen species were only detected at low concentrations in shallow groundwater,averaging at 3.6 mg/L NH4-N and 1.8 mg/L NO3-N. Measurement results supported by PHREEQC-modeling indicated cation exchange, denitrification, and anaerobic ammonium oxidation coupled with partial denitrification as major nitrogen removal pathways. Despite the current removal capacity, the excessive nitrogen fertilization may pose a future threat to groundwater quality. Surface water quality improvements are therefore recommended in conjunction with simultaneous monitoring of nitrate in the aquifer, and reduced agricultural N-inputs should be considered.