Machine Learning in Evaluating Multispectral Active Canopy Sensor for Prediction of Corn Leaf Nitrogen Concentration and Yield

Applying the optimum rate of fertilizer nitrogen (N) is a critical factor for field management. Multispectral information collected by active canopy sensors can potentially indicate the leaf N status and aid in predicting grain yield. Crop Circle multispectral data were acquired with the purpose of measuring the reflectance data to calculate vegetation indices (VIs) at different growth stages. Applying the optimum rate of fertilizer N can have a considerable impact on grain yield and profitability. The objectives of this study were to evaluate the reliability of a handheld Crop Circle ACS-430, to estimate corn leaf N concentration and predict grain yield of corn using machine learning (ML) models. The analysis was conducted using four ML models to identify the best prediction model for measurements acquired with a Crop Circle ACS-430 field sensor at three growth stages. Four fertilizer N levels from deficient to excessive in 50/50 spilt were applied to corn at 1–2 leaves, with visible leaf collars (V1-V2 stage) and at the V6-V7 stage to establish widely varying N nutritional status. Crop Circle spectral observations were used to derive 25 VIs for different growth stages (V4, V6, and VT) of corn at the W. B. Andrews Agricultural Systems farm of Mississippi State University. Multispectral raw data, along with Vis, were used to quantify leaf N status and predict the yield of corn. In addition, the accuracy of wavelength-based and VI-based models were compared to examine the best model inputs. Due to limited observed data, the stratification approach was used to split data to train and test set to obtain balanced data for each stage. Repeated cross validation (RCV) was then used to train the models. Results showed that the Simplified Canopy Chlorophyll Content Index (SCCCI) and Red-edge ratio vegetation index (RERVI) were the most effective VIs for estimating leaf N% and that SCCCI, Red-edge chlorophyll index (CIRE), RERVI, Soil Adjusted Vegetation Index (SAVI), and Normalized Difference Vegetation Index (NDVI) were the most effective VIs for predicting corn grain yield. Additionally, among the four ML models utilized in this research, support vector regression (SVR) achieved the most accurate results for estimating leaf N concentration using either spectral bands or VIs as the model inputs.

Irrigation with municipal wastewater as a suitable solution for safflower cultivation in arid regions

In order to study the effect of different manure and chemical fertilizer levels on qualitative and quantitative characteristics of safflower in the condition of irrigation with municipal wastewater, an experiment was conducted as split plot basis of randomized complete design in Lakhshah region locate in Zahedan city, Iran. The treatments were comprised of two levels of irrigation, W1= Well water and W2= Treated wastewater, in main plots and sub plots consisted of F1: control (without consumption of manure and chemical fertilizer), F2: Recommended manure, F3: Half of recommended manure and chemical fertilizer (N, P and K), and F4: Recommended chemical fertilizer (N, P and K). The results showed that Treatment of treated wastewater had a positive and significant influence on all yield components, and the most influence was shown on 1000 seed weight. Also, irrigation with wastewater significantly increases the dry and fresh yield and grain yield of safflower than ordinary water. Among the fertilizer treatments, complete treatment of chemical fertilizer N, P and K had the greatest effect on increase of yield and grain yield components. In this experiment, water treatment hadn’t significant effect on accumulation of Cr, pb, Fe and Mn in safflower grain, and soil. While, fertilizer treatment had only a significant influence on the accumulation of Fe and Mn in safflower grain, but between these treatments wasn’t saw any significant difference on the accumulation of Cr and pb. In general, the results of this experiment showed that irrigation with wastewater and application of complete fertilizer with manure is recommended.

Competition of Plants and Microorganisms for Added Nitrogen in Different Fertilizer Forms in a Semi-Arid Climate

In nitrogen (N) -limited agricultural systems, a high microbial immobilization of applied fertilizer-N can limit its availability to plants. However, there is scarce information on the effect of the form of fertilizer used on the plant–microorganism competition in clay-rich soils under a severe semi-arid climate. In a field study, we investigated the wheat–microorganism competition after the direct application of NH415NO3 closely to seeds in arable fields in North Kazakhstan, documenting the effect of the use of liquid versus granular fertilizer and mini-tillage versus no-tillage. Our results barely showed any fertilizer-N translocation in the soil. Plants outcompete microorganisms for fertilizer-N during the vegetation period. Microbial-to-plant 15N ratios revealed a predominant fertilizer-15N uptake by plants. The strong competition for N was mainly related to the placement of the fertilizer close to the seeds. Moreover, the long time interval between fertilization and sampling enhanced the competition for N, meaning that previously microbially immobilized N became available to plants through the death of microorganisms and their subsequent mineralization. The fertilizer distribution between microorganisms and plants did depend on the form of fertilizer used, owing to the good solubility of granular fertilizer. The smaller fertilizer-N uptake under the no-tilling condition was probably due to the more intense soil compaction, which caused a reduction in plant growth. The application of fertilizer close to the seeds and the small fertilizer translocation during the vegetation period ultimately resulted in a high level of plant-N being derived from the fertilizer.

Intercropping and Nitrogen Fertilization Altered the Patterns of Leaf Senescence in Sorghum

Leaf senescence regulates grain yield. However, the modulation of leaf senescence in sorghum under legume-based intercrop systems and nitrogen (N) fertilization is not known. The objective of the study was to investigate the effect of intercropping two sorghum (Gadam and Serena) and cowpea (K80, M66) varieties and sole cropping systems and different fertilizer N rates (0, 40, and 80 kg·N·ha−1) on the time course of postflowering sorghum leaf senescence and understand how senescence modulates grain yield. The experiment was laid out in a randomized complete block design with a split-plot arrangement with three replications. Leaf senescence was assessed from flowering to maturity at (a) whole-plant level by the visual scoring of green leaves and (b) flag leaf scale by measuring leaf greenness with a SPAD 502 chlorophyll meter. A logistic function in SigmaPlot was fitted to estimate four traits of leaf senescence, including minimum and maximum SPAD (SPADmin, SPADmax), time to loss of 50% SPADmax (EC50), and the rate of senescence. Irrespective of the cowpea variety, intercropping reduced sorghum grain yield by 50%. The addition of N increased yield by 27% but no effect was detected between 40 and 80 kg·N ha−1. Intercropping delayed leaf senescence at the whole plant by 0.2 leaves plant−1 day−1 but reduced SPADmax of the flag by 8 SPAD units and rate of senescence by 4 SPAD units day−1 compared with sole crop system. Fertilizer N delayed leaf senescence ( P ≤ 0.05 ) at whole-plant and flag leaf scales. Cropping System × nitrogen modulated senescence at whole-plant and flag leaf scales and sorghum grain yield but marginally influenced other traits. While EC50 did not correlate with grain yield, faster rates of senescence and leaf greenness were associated with high yield under the sole crop system. Overall, N was the main factor in driving sorghum leaf senescence while the intercropping effect on senescence was nonfunctional. Effects of competition in sorghum-legume intercropping and source-sink relationships on the patterns of leaf senescence deserve further investigation.

Optimalisasi Dosis Pupuk Tunggal dan Pupuk Kandang untuk Produksi Bawang Putih di Dataran Tinggi

The addition of nutrients for garlic plants consists of two type, namely the application of anorganic fertilizers in the form of single fertilizers N, P, K and organic fertilizers such as manure. The purpose of this study was to obtain the right dose of single fertilizer N, P, K and chicken manure. The experiment was arranged using a Randomized Block Design with 4 replications. The treatments consisted of 9 treatment combinations consisting of A = 100% single fertilizer + 15 tons of manure, B = 100% single fertilizer + 10 tons of manure, C = 100% single fertilizer + 5 tons of manure, D = 75% single fertilizer + 15 tons of manure, E = 75% single fertilizer + 10 tons of manure, F = 75% single fertilizer + 5 tons of manure, G = 50% single fertilizer + 15 tons of manure, H = 50% single fertilizer + 10 tons of manure, I = 50% single fertilizer + 5 tons of manure. The dose of 100% single fertilizer was SP36 375 kg.ha-1, ZA 1.144 kg.ha-1and KCl 200 kg.ha-1. The type of manure used is chicken manure. The results showed that doses of 75% and 100% of single fertilizer combined with 15 ton.ha-1 resulted in the wet and dry weight of the stover, the diameter and weight of the tubers, which were the same, respectively, the dry weight of the stover 32,57 grams and 39,40 grams, the dry weight of the stover. 17,43 grams and 17,63 grams, tuber diameter 33,09 and 33,13, tuber weight 14,07 grams and 14,30 grams. These results tend to be higher than other treatments. 75% single fertilizer and 15 ton.ha-1 chicken manure can be recommended for fertilization in garlic production.

Crop Field Level Estimation of Nitrogen Input from Fertilizer Use in Jeju Island, South Korea: Management Methods to Prevent Groundwater NO3-N Contamination

The application of synthetic nitrogen (N) fertilizers has boosted crop yields globally. However, it has also imposed on environmental pollution problems. An estimation of actual fertilizer N inputs at the crop field level is needed to establish effective N management plans to control groundwater NO3-N contamination. Here, a survey to collect the types of cultivated crop and fertilizer application rate was conducted during 2016–2018, covering 44,253 small crop fields (7730 ha) in the western part (Hanrim and Hankyung regions) of Jeju Island, South Korea. Foreign vegetables, citrus fruits, and bulb vegetables are the major crop types grown in the total cultivated areas of 2165.6 ha, 1718.7 ha, and 944.9 ha, respectively. For several crops (green garlic, potato, and chives), the over-use of N fertilizers is observed, the amount of which is 1.73–4.95 times greater than the standard fertilizer application rate. The highest level of fertilizer N input is observed for bulb vegetables in both the regions (Hanrim: 500.5 kg/ha, Hankyung: 487.1 kg/ha), with nearly 80% of the N fertilizer input turned into surplus N loading. A comparison between a spatial interpolation map of the fertilizer N input and that of the groundwater NO3-N concentration implies that the excessive use of synthetic fertilizer results in the degradation of groundwater quality by NO3-N. N management plans for the study area are suggested based on the N fertilizer input at the crop field level. This study highlights that sustainable N management plans should be arranged at the crop field level, considering the spatial heterogeneity of N fertilizer use.

Fixed-time corrective dose fertilizer nitrogen management in wheat using atLeaf meter and leaf colour chart

Fertilizer nitrogen (N) management in any region following standard general recommendations discount the fact that crop response to N varies between sites and seasons. To devise field-specific N management in wheat at jointing stage (Feekes 6 growth stage) using atLeaf meter and leaf colour chart (LCC), eight field experiments were conducted in three wheat seasons during 2017–2020 in the West Delta of Egypt. In the first two seasons, four experiments consisted of treatments with a range of fertilizer N application levels from 0 to 320 kg N ha−1. Monitoring atLeaf and LCC measurements at Feekes 6 growth stage in plots with different yield potentials allowed formulation of different criteria to apply field-specific and crop need-based fertilizer N doses. In the four experiments conducted in the third season in 2019/20, different field-specific N management strategies formulated in 2017/18 and 2018/19 wheat seasons were evaluated. In the atLeaf-based fertilizer N management experiment, prescriptive application of 40 kg N ha−1 at 10 days after seeding (DAS) and 60 kg N ha−1 at 30 DAS followed by application of an adjustable dose at Feekes 6 stage computed by multiplying the difference of atLeaf measurements of the test plot and the N-sufficient plot with 42.25 (as derived from the functional model developed in this study), resulted in grain yield similar or higher to that obtained by following the standard treatment. The LCC-based strategy to apply field-specific fertilizer N at Feekes 6 stage consisted of applying 150, 100 or 0 kg N ha−1 based on LCC shade equal to or less than 4, between 4 and 5 or equal to or more than 5, respectively. Both atLeaf- and LCC-based fertilizer N management strategies not only recorded the highest grain yield levels but also resulted in higher use efficiency with 57–60 kg N ha−1 in average less fertilizer use than the standard treatment.

Do Water and Nitrogen Management Practices Impact Grain Quality in Maize?

Concomitantly pursuing superior maize (Zeamays L.) productivity with grain quality is essential for food security. Therefore, this study provides a meta-analysis of 21 studies assembled from the scientific literature to tackle the effect of the two most limiting factors for maize production, water and nitrogen (N), and their impacts on grain quality composition, herein focused on protein, oil, and starch concentrations. Water stress levels resulted in erratic responses both in direction and magnitude on all the grain quality components, plausibly linked to a different duration, timing, and intensity of water stress treatments. Nitrogen fertilization more consistently affected the grain protein concentration, with a larger effect size for protein as fertilizer N levels increased (protein change of +14% for low, ≤70 kg N ha−1; +21% for medium, >70–150 kg N ha−1; and +24% for high, >150 kg N ha−1). Both starch and oil grain concentrations presented less variation to fertilizer N levels. The positive protein–oil correlation (r = 0.49) permitted to infer that although the oil concentration may reach a plateau (8%), further increases in protein are still possible. Augmented research on grain quality is warranted to sustain food production but with both high nutritional and energetic value for the global demand.

Reactive Nitrogen Releases And Nitrogen Footprint During The Life-Cycles of Intensive Vegetable Production Affected By Human Feces Slurry Substitution

Evaluating the sustainability of vegetable production is crucial to secure future food supply. A two-year field study of four different vegetable crops was performed to investigate the effects of inorganic fertilizer and human feces slurry at different ratios on vegetable yields, reactive gaseous nitrogen emissions (GNrEs), reactive nitrogen (Nr) footprint and net ecosystem-economic income (NEEI) by using life-cycle analysis. Four fertilization strategies were studied, including: CK (no fertilization); CF (inorganic fertilization); CHF1 (human feces slurry/inorganic fertilizer, N ratio=1:7); and CHF2 (human slurry/inorganic fertilizer, N ratio=1:3). Results showed that compared with CF treatment, both CHF1 and CHF2 treatments increased the N2O+NO emissions by 11.8 % and 32.4 % on average, while decreased the vegetable yields by 6.7 % and 7.4 %, respectively. Moreover, the addition of human feces slurry increased the proportions of Nr footprint by 6.6 % (CHF1) and 2.9 % (CHF2) in comparison with CF treatment group. However, although CHF2 treatment significantly increased the values of GNrEs and reactive gaseous nitrogen intensity (GNrI) by 8.4 % and 12.5 %, respectively, in relation to those in CF treatment group, it still increased farmers’ income by 16,404 CNY ha−1. These findings suggest that although human feces slurry incorporation could not mitigate Nr releases, the appropriate ratio of inorganic fertilizer and human feces slurry (CHF2) is able to improve net economic income (NEI) and NEEI during intensive vegetable production. Nevertheless, the relationship between combinatorial treatment of inorganic fertilizer and human feces slurry and mitigation of Nr release should be explored further.