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.

Effects of short-term nitrogen and phosphorus addition on leaf stoichiometry of a dominant alpine grass

The effects of increasing nitrogen (N) and phosphorus (P) deposition on the nutrient stoichiometry of soil and plant are gaining improving recognition. However, whether and how the responses of N cycle coupled with P of the soil–plant system to external N and P deposition in alpine grassland is still unclear. A short-term external N and P addition experiment was conducted in an alpine grazing grassland in the KunLun Mountain to explore the effects of short-term N and P addition on the nutrient stoichiometry in soil and plant. Different rates of N addition (ranging from 0.5 g N m−2 yr−1 to 24 g N m−2 yr−1) and P addition (ranging from 0.05 g N m−2 yr−1 to 3.2 g P m−2 yr−1) were supplied, and the soil available N, P, leaf N and P stoichiometry of Seriphidium rhodanthum which dominant in the alpine ecosystem were measured. Results showed that N addition increased soil inorganic N, leaf C, leaf N, and leaf N:P ratio but decreased soil available P and leaf C:P. Furthermore, P addition increased soil available P, leaf P, soil inorganic N, leaf N, and leaf C and reduced leaf C:N, C:P, and N:P ratios. Leaf N:P was positively related to N addition gradient. Leaf C:P and leaf N:P were significantly negatively related to P addition gradient. Although external N and P addition changed the value of leaf N:P, the ratio was always lower than 16 in all treatments. The influences of P addition on soil and plant mainly caused the increase in soil available P concentration. In addition, the N and P cycles in the soil–plant system were tightly coupled in P addition but decoupled in N addition condition. The nutrient stoichiometry of soil and leaf responded differently to continuous N and P addition gradients. These data suggested that the alpine grazing grassland was limited by P rather than N due to long-term N deposition and uniform fertilization. Moreover, increasing P addition alleviated P limitation. Therefore, the imbalanced N and P input could change the strategy of nutrient use of the grass and then change the rates of nutrient cycling in the alpine grassland ecosystem in the future.

Real-Time Detection of Rice Growth Phase Transition for Panicle Nitrogen Application Timing Assessment

Nitrogen (N) topdressing at the early reproductive phase (ER) is beneficial for rice yield. However, the ER overlaps with the late vegetative phase (LV) and is, thus, difficult to be recognized by human observation. Therefore, this study aimed to establish a high-temporal-resolution approach to determine the LV and ER via hyperspectral proximal sensing. Firstly, this research measured the leaf cover area (LCA), leaf dry weight (LDW), chlorophyll content (SPAD), leaf N content (LNC), and leaf N accumulation (LNA) to investigate the physical and physiological changes of the rice plant during growth phase transition. It could be summarized that the LCA would be maximally extended before ER, the leaf growth would be retarded after LV, and leaves turned from green to yellowish-green resulting from N translocation. These phenomena were expected to be detected by the hyperspectral sensor. In order to capture the variation of spectral information while eliminating redundant hyperspectral wavelengths, feature extraction (FE) and feature selection (FS) were conducted to reduce the data dimension. Meanwhile, the implications of the features were also inferenced. Three principal components, which correlated with the rice plant’s physical and physiological traits, were extracted for subsequent modeling. On the aspect of FS, 402, 432, 579, and 696 nm were selected as the predictors. The 402 nm wavelength significantly correlated with leaf cover area to some extent (p < 0.09), and 432 nm had no significant correlation with all of the measured plant traits (p > 0.10). The 579 nm and 696 nm wavelengths were negatively correlated with SPAD and LNC (p < 0.001). In addition, 696 nm was also negatively correlated with LNA (p < 0.05). Finally, the logistic regression, random forest (RF), and support vector machine (SVM) algorithms were adopted to solve the binary classification problem. The result showed that the feature extraction-based logistic regression (FE-logistic) and support vector machine (FE-SVM) were competent for growth phase discrimination (accuracy > 0.80). Nonetheless, taking the detrimental effects of applying N at LV into consideration, the feature extraction-based support vector machine (FE-SVM) was more appropriate for the timing assessment of panicle fertilizer application (sensitivity > 0.90; specificity > 0.80; precision > 0.80).

In Vitro Interactions of Costus speciosus (J. Koenig) Sm., Cymbopogon citratus (Dc. Ex Nees) Stapf. and Tabernaemontana coronaria (L.) Willd. with First-Line Anti-Tuberculosis Drugs Against Mycobacterium tuberculosis H37rv

Global tuberculosis (TB) burden underscores the importance of developing new effective anti-TB drugs. This study was concerned with prospecting for potential anti-TB agents from Malaysian medicinal plants. In our previous study, we have reported that n-hexane fractions of Costus speciosus (C. speciosus) (J. Koening) Sm., Cymbopogon citratus (C. citratus ) (DC.) Stapf. and Tabernaemontana coronaria (T. coronaria) (Jacq.) posses promising anti-TB activity against Mycobacterium tuberculosis (M. tuberculosis) H37Rv with minimum inhibitory concentrations (MICs) of 200–100 µg/mL. This study aimed to investigate the interactions of these active fractions with first-line anti-TB drugs (isoniazid, rifampicin, ethambutol and streptomycin) against M. tuberculosis H37Rv using the microdilution checkerboard method. C. citratus (stem-rhizome) n-hexane fraction exhibited synergism with all drugs except ethambutol which showed additive interaction. Synergistic was also observed when C. speciosus (stem-flower) n-hexane and T. coronaria (leaf) n-hexane fractions in combination with rifampicin. C. speciosus (stem-flower) n-hexane and T. coronaria (leaf) n-hexane exhibited additive interaction with isoniazid, ethambutol and streptomycin. Hence, these active plants are worthy of further investigations for the discovery of anti-TB drug leads.

Estimation of Critical Nitrogen Concentration Based on Leaf Dry Matter in Drip Irrigation Spring Maize Production in Northern China

Background: The application of nitrogen (N) fertilizer not only increases crop yield but also improves the N utilization efficiency. The critical N concentration (Nc) can be used to diagnose crops N nutritional status. The Nc dilution curve model of maize was calibrated with leaf dry matter (LDM) as the indicator, and the performance of the model for diagnosing maize N nutritional status was further evaluated. Three field experiments were carried out in two sites between 2018 and 2020 in Ningxia Hui Autonomous Region with a series of N levels (application of N from 0 to 450 kg N ha-1). Two spring maize cultivars, i.e., Tianci19 (TC19) and Ningdan19 (ND19), were utilized in the field experiment. Results: The results showed that a negative power function relationship existed between LDM and leaf N concentration (LNC) for spring maize under drip irrigation. The Nc dilution curve equation was divided into two parts: when the LDM < 1.11 t ha-1, the constant leaf Nc value was 3.25%; and when LDM > 1.11 t ha-1, the Nc curve was 3.33*LDM-0.24. Conclusion: The LDM based Nc curve can well distinguish data the N-limiting and non-N-limiting N status of maize, which was independent with maize varieties, growing seasons and stages. Additionally, the N nutrition index (NNI) had a significant linear correlation with the relative leaf dry matter (RLDM). This study revealed that the LDM based Nc dilution curve could accurately identify spring maize N status under drip irrigation. NNI can thus, be used as a robust and reliable tool to diagnose N nutritional status of maize.

Presence of N-fixing neighbors increases leaf N and δ13C in Castilleja applegatei, a root hemiparasite

Parasitic plants are known for their high transpiration rates and low water use efficiency (WUE), which the N-parasitism hypothesis posits is driven by N limitation. Thus, availability of N-fixing hosts may affect parasite’s WUE and in turn impact the surrounding plant community. Here, I investigate how the availability of an N-fixing host affects the root hemiparasite, Castilleja applegatei, and examines host-mediated effects on community structure and soil moisture. I surveyed plant diversity and percent cover and measured soil moisture in 120 1 × 1 m plots within Sagehen Experimental Forest, CA. Fifty percent of the plots included C. applegatei. In a subset of plots, I measured leaf N, C/N, δ13C, and δ15N in C. applegatei and in one N-fixer (Ceanothus prostratus) and two non-N-fixing plants (Artemisia tridentata and Wyethia mollis). In C. applegatei availability of N-fixing hosts corresponded to a significant increase in leaf %N, a distinct δ15N signature, and an increase in δ13C (which typically signifies an increased WUE). The presence of parasites was associated with a marginally significant decrease in WUE in N-fixing neighbors, but had no effect on the two non-N-fixing species. The presence of parasites did not impact diversity, percent cover, or soil moisture. These results broadly support the N-parasitism hypothesis and indicate that host type can affect parasite’s physiology and therefore have the potential to mediate parasite’s effects in the community; however, community-level impacts were not found here.

Spatial Distribution Patterns and Driving Factors of Plant Biomass and Leaf N, P Stoichiometry on the Loess Plateau of China

Understanding the geographic patterns and potential drivers of leaf stoichiometry and plant biomass is critical for modeling the biogeochemical cycling of ecosystems and to forecast the responses of ecosystems to global changes. Therefore, we studied the spatial patterns and potential drivers of leaf stoichiometry and herb biomass from 15 sites spanning from south to north along a 500 km latitudinal gradient of the Loess Plateau. We found that leaf N and P stoichiometry and the biomass of herb plants varied greatly on the Loess Plateau, showing spatial patterns, and there were significant differences among the four vegetation zones. With increasing latitude (decreasing mean annual temperature and decreasing mean precipitation), aboveground and belowground biomass displayed an opening downward parabolic trend, while the root–shoot ratio gradually decreased. Furthermore, there were significant linear relationships between the leaf nitrogen (N) and phosphorus (P) contents and latitude and climate (mean annual rainfall and mean annual temperature). However, the leaf N/P ratio showed no significant latitudinal or climatic trends. Redundancy analysis and stepwise regression analysis revealed herb biomass and leaf N and P contents were strongly related to environmental driving factors (slope, soil P content and latitude, altitude, mean annual rainfall and mean annual temperature). Compared with global scale results, herb plants on the Loess Plateau are characterized by relatively lower biomass, higher N content, lower P content and a higher N/P ratio, and vegetative growth may be more susceptible to P limitation. These findings indicated that the remarkable spatial distribution patterns of leaf N and P stoichiometry and herb biomass were jointly regulated by the climate, soil properties and topographic properties, providing new insights into potential vegetation restoration strategies.

Photosynthetic induction upon transfer from low to high light is affected by leaf nitrogen content in tomato

The response of photosynthetic CO2 assimilation to changes of illumination affects plant growth and crop productivity under natural fluctuating light conditions. However, the effects of nitrogen (N) supply on photosynthetic physiology after transition from low to high light are seldom studied. To elucidate this, we measured gas exchange and chlorophyll fluorescence under fluctuating light in tomato (Solanum lycopersicum) seedlings grown with different N conditions. After transition from low to high light, the induction speeds of net CO2 assimilation (AN), stomatal conductance (gs) and mesophyll conductance (gm) delayed with the decline in leaf N content. The times to reach 90% of maximum AN, gs and gm were negatively correlated to leaf N content. This delayed photosynthetic induction in plants grown under low N concentration was mainly caused by the slow induction response of gm rather than that of gs. Furthermore, the photosynthetic induction upon transfer from low to high light was hardly limited by photosynthetic electron flow. These results indicate that decreased leaf N content declines carbon gain under fluctuating light in tomato. Increasing the induction kinetics of gm has the potential to enhance the carbon gain of field crops grown in infertile soil.

The Effect of Low Irradiance on Leaf Nitrogen Allocation and Mesophyll Conductance to CO2 in Seedlings of Four Tree Species in Subtropical China

Low light intensity can lead to a decrease in photosynthetic capacity. However, could N-fixing species with higher leaf N contents mitigate the effects of low light? Here, we exposed seedlings of Dalbergia odorifera and Erythrophleum fordii (N-fixing trees), and Castanopsis hystrix and Betula alnoides (non-N-fixing trees) to three irradiance treatments (100%, 40%, and 10% sunlight) to investigate the effects of low irradiance on leaf structure, leaf N allocation strategy, and photosynthetic physiological parameters in the seedlings. Low irradiance decreased the leaf mass per unit area, leaf N content per unit area (Narea), maximum carboxylation rate (Vcmax), maximum electron transport rate (Jmax), light compensation point, and light saturation point, and increased the N allocation proportion of light-harvesting components in all species. The studied tree seedlings changed their leaf structures, leaf N allocation strategy, and photosynthetic physiological parameters to adapt to low-light environments. N-fixing plants had a higher photosynthesis rate, Narea, Vcmax, and Jmax than non-N-fixing species under low irradiance and had a greater advantage in maintaining their photosynthetic rate under low-radiation conditions, such as under an understory canopy, in a forest gap, or when mixed with other species.