Leaf area index (LAI) and leaf dry matter (LDM) are important indices of crop growth. Real-time, nondestructive monitoring of crop growth is instructive for the diagnosis of crop growth and ...prediction of grain yield. Unmanned aerial vehicle (UAV)-based remote sensing is widely used in precision agriculture due to its unique advantages in flexibility and resolution. This study was carried out on wheat trials treated with different nitrogen levels and seeding densities in three regions of Jiangsu Province in 2018–2019. Canopy spectral images were collected by the UAV equipped with a multi-spectral camera during key wheat growth stages. To verify the results of the UAV images, the LAI, LDM, and yield data were obtained by destructive sampling. We extracted the wheat canopy reflectance and selected the best vegetation index for monitoring growth and predicting yield. Simple linear regression (LR), multiple linear regression (MLR), stepwise multiple linear regression (SMLR), partial least squares regression (PLSR), artificial neural network (ANN), and random forest (RF) modeling methods were used to construct a model for wheat yield estimation. The results show that the multi-spectral camera mounted on the multi-rotor UAV has a broad application prospect in crop growth index monitoring and yield estimation. The vegetation index combined with the red edge band and the near-infrared band was significantly correlated with LAI and LDM. Machine learning methods (i.e., PLSR, ANN, and RF) performed better for predicting wheat yield. The RF model constructed by normalized difference vegetation index (NDVI) at the jointing stage, heading stage, flowering stage, and filling stage was the optimal wheat yield estimation model in this study, with an R2 of 0.78 and relative root mean square error (RRMSE) of 0.1030. The results provide a theoretical basis for monitoring crop growth with a multi-rotor UAV platform and explore a technical method for improving the precision of yield estimation.
The accurate estimation and timely diagnosis of crop nitrogen (N) status can facilitate in-season fertilizer management. In order to evaluate the performance of three leaf and canopy optical sensors ...in non-destructively diagnosing winter wheat N status, three experiments using seven wheat cultivars and multi-N-treatments (0–360 kg N ha−1) were conducted in the Jiangsu province of China from 2015 to 2018. Two leaf sensors (SPAD 502, Dualex 4 Scientific+) and one canopy sensor (RapidSCAN CS-45) were used to obtain leaf and canopy spectral data, respectively, during the main growth period. Five N indicators (leaf N concentration (LNC), leaf N accumulation (LNA), plant N concentration (PNC), plant N accumulation (PNA), and N nutrition index (NNI)) were measured synchronously. The relationships between the six sensor-based indices (leaf level: SPAD, Chl, Flav, NBI, canopy level: NDRE, NDVI) and five N parameters were established at each growth stages. The results showed that the Dualex-based NBI performed relatively well among four leaf-sensor indices, while NDRE of RS sensor achieved a best performance due to larger sampling area of canopy sensor for five N indicators estimation across different growth stages. The areal agreement of the NNI diagnosis models ranged from 0.54 to 0.71 for SPAD, 0.66 to 0.84 for NBI, and 0.72 to 0.86 for NDRE, and the kappa coefficient ranged from 0.30 to 0.52 for SPAD, 0.42 to 0.72 for NBI, and 0.53 to 0.75 for NDRE across all growth stages. Overall, these results reveal the potential of sensor-based diagnosis models for the rapid and non-destructive diagnosis of N status.
Establishing the universal critical nitrogen (N
) dilution curve can assist in crop N diagnosis at the regional scale. This study conducted 10-year N fertilizer experiments in Yangtze River Reaches ...to establish universal N
dilution curves for Japonica rice based on simple data-mixing (SDM), random forest algorithm (RFA), and Bayesian hierarchical model (BHM), respectively. Results showed that parameters
and
were affected by the genetic and environmental conditions. Based on RFA, highly related factors of
(plant height, specific leaf area at tillering end, and maximum dry matter weight during vegetative growth period) and
(accumulated growing degree days at tillering end, stem-leaf ratio at tillering end, and maximum leaf area index during vegetative growth period) were successfully applied to establish the universal curve. In addition, representative values (
) were selected from posterior distributions obtained by the BHM approach to explore universal parameters
and
. The universal curves established by SDM, RFA, and BHM-
were verified to have a strong N diagnostic capacity (N nutrition index validation
≥ 0.81). In summary, compared with the SDM approach, RFA and BHM-
can greatly simplify the modeling process (e.g., defining N-limiting or non-N-limiting groups) while maintaining a good accuracy, which are more conducive to the application and promotion at the regional scale.
•The NDVITs constructed by spectral and textural information performed well in wheat LNC monitoring and GPC estimation.•Textural information can assist spectral information to monitor wheat LNC and ...GPC effectively.•ANN model combining spectra, texture and ecological factor performed well in wheat GPC estimation.•Effective ecological factors are good predictors to improve the prediction accuracy of wheat GPC.
Nitrogen is an essential element of wheat growth and grain quality. Leaf nitrogen content (LNC), a critical monitoring indicator of crop nitrogen status, plays a reference role for later estimations of grain protein content (GPC). Developments in unmanned aerial vehicle (UAV) platforms and multispectral sensors have provided new approaches for LNC monitoring and GPC estimation, with great convenience for assessing the nutritional status of plants and grains without traditional destructive sampling. The objective of this study was to evaluate the feasibility of wheat LNC monitoring and GPC estimation based on UAV multispectral imagery. Wheat experiments were carried out in Xinghua, Kunshan and Suining of Jiangsu Province during 2018−2019 and in Rugao of Jiangsu Province during 2020−2021 with different varieties and nitrogen application rates. Remote sensing images were obtained by a multi-rotor UAV carrying a multispectral camera. The destructive sampling method was used to collect LNC, GPC and other field data. Wheat LNC monitoring and GPC estimation models were established after selection of the optimal indicators. Different modelling methods were used for the comparative analysis, including unitary linear regression, multiple linear regression and artificial neural network (ANN) methods. Three techniques were adopted to improve the GPC prediction accuracy: (1) multiple factors were substituted for single factor for the prediction; (2) texture information was added through further imagery mining; and (3) ecological factors were considered to improve the prediction mechanism. The results showed that the use of UAV-based Airphen multispectral imagery had a good effect on wheat LNC monitoring and GPC estimation. The vegetation indices constructed by red-edge and near-infrared bands had good performances in LNC monitoring and GPC estimation. The addition of texture information and ecological factors further improved the modelling accuracy. In this study, the optimal wheat GPC estimation model was established by NDVI (675, 730) at the jointing stage, NDVIT (730mea., 850) at the booting stage, NDVIT (730mea., 850) at the flowering stage and NDVI (730, 850) at the early filling stage. The modelling R2, validation R2 and relative root mean square error (RRMSE) reached 0.662, 0.7445 and 0.0635, respectively. The results provide a reference for crop LNC monitoring and GPC estimation based on UAV multispectral imagery.
The investigation of ecosystem respiration (RE) and its vital influential factors along with the timely and accurate detection of spatiotemporal variations in RE are essential for guiding ...agricultural production planning. RE observation in the plot region is primarily based on the laborious chamber method. However, upscaling the spatial-temporal estimates of RE at the canopy scale is still challenging. The present study conducted a field experiment to determine RE using the chamber method. A multi-rotor unmanned aerial vehicle (UAV) equipped with a multispectral camera was employed to acquire the canopy spectral data of wheat during each RE test experiment. Moreover, the agronomic indicators of aboveground plant biomass, leaf area index, leaf dry mass as well as agrometeorological and soil data were measured simultaneously. The study analyzed the potential of multi-information for estimating RE at the field scale and proposed two strategies for RE estimation. In addition, a semiempirical, yet Lloyd and Taylor-based, remote sensing model (LT1-NIRV) was developed for estimating RE observed across different growth stages with a small margin of error (coefficient of determination R2 = 0.60–0.64, root-mean-square error RMSE = 285.98–316.19 mg m−2 h−1). Further, five machine learning (ML) algorithms were utilized to independently estimate RE using two different datasets. The rigorous analyses, which included statistical comparison and cross-validation for estimating RE, confirmed that the XGBoost model, with the highest R2 and lowest RMSE (R2 = 0.88 and RMSE = 172.70 mg m−2 h−1), performed the best among the evaluated ML models. The LT1-NIRV model was less effective in estimating RE compared with the other ML models. Based on this comprehensive comparison analysis, the ML model can successfully estimate variations in wheat field RE using high-resolution UAV multispectral images and environmental factors from the wheat cropland system, thereby providing a valuable reference for monitoring and upscaling RE observations.
Display omitted
•Abiotic and biotic traits greatly determine variations in ecosystem respiration (RE).•LT1–NIRV model was reliable in estimating the RE of winter wheat field.•XGBoost model exhibited the best performance in estimating CO2 fluxes.
In wheat-rice rotation, late sowing and excessive nitrogen (N) application lead to low annual yield and additional fertilizer waste. A comprehensive assessment of yield sustainability, N use ...efficiency, N balancing mechanism, and economic benefit is urgent.
To explore the feasibility of optimizing N application and sowing date to improve yield, N use efficiency, and economic benefit in wheat-rice rotation.
A two-year experiment of wheat-rice rotation was conducted in China, involving four N application rates (0, 180, 240, and 300 kg ha−1), three sowing dates (normal, delayed, and late sowing), three planting density (1.2 × 104, 1.8 × 104, and 2.4 × 104 seeds ha−1) for wheat (Yangmai-23), and four N application rates (0, 135, 270, and 405 kg ha−1), three sowing dates (normal, delayed, and late sowing), and three varieties (Yongyou-2640, Wuyunjing-32, and Nanjing-9108) for rice. Treatments were imposed in a split-plot experiment design with three replications (except N0). Soil information, N uptake, and yield were obtained through field survey and sampling. In addition, N balance was studied based on measured data and Denitrification-Decomposition (DNDC) model. Reactive N emissions (NH3, N2O, and NO) simulated by DNDC were converted into environmental damage costs for annual economic analysis.
Delaying sowing could reduce annual yield from 6.14% to 13.72%, while appropriate N application can mitigate this trend. However, delaying sowing promoted soil N accumulation and yield sustainability. N fertilizer addition and late sowing would reduce annual N physiologic efficiency by 45.98%, N recovery efficiency by 42.02%, and N agronomic efficiency by 68.10%, leading to N surplus. Applying more N not only increased annual yield (24.85%–39.44%) and profit (74.27%–162.16%) but also brought more reactive N damage cost (7.40%–25.14%). In this study, the appropriate N application rate for delayed sowing (WR-S2) and late sowing (WR-S3) were 510–705 kg N ha−1 and 315–510 kg N ha−1, respectively.
Optimizing N fertilizer and sowing date is an easy-followed strategy for improving yield, N use efficiency, and economic benefit in wheat-rice rotation, which is highly-consistent with United Nations Sustainable Development Goals. This strategy is simple to implement for policy formulation on precision agriculture and highly-effective to manage.
Display omitted
•Excessive nitrogen application and delayed sowing date threaten the productivity and sustainability of wheat-rice rotations.•Adaptive strategies were adopted to mitigate yield decrease, economic loss, and environmental damage in wheat-rice rotation.•Nitrogen use and profit could be improved while maintaining yield based on optimization of fertilization and sowing date.•Coordination of fertilization and sowing date helps to achieve a high-yield, high-efficiency, and sustainable production.•Optimizing nitrogen fertilizer and sowing date is simple for policy formulation and highly effective to manage.
Wheat and rice are the main food crops in China. Appropriate nitrogen (N) fertilizer can effectively promote the crop growth, whereas excessive use has repercussions on yield formation and ...environmental preservation. Therefore, timely assessment of crop N status and precise N application management are of paramount importance.
The study aims to assess the impacts of N fertilizer on N accumulation and spectral dynamics in wheat and rice, and investigate the feasibility of real-time crop N status diagnosis using unmanned aerial vehicle (UAV) spectra and devise subsequent managements.
Ten experiments were conducted in Xinghua City and Lianyungang City from 2017 to 2020, involving different N fertilizer rates (0–405 kg N ha−1) and various cultivars. Field sampling was carried out simultaneously with UAV image acquisition, and the crop dry matter and N concentration were obtained by indoor analysis.
Normalized difference red-edge index (NDRE) and N nutrition index (NNI) demonstrated a robust power function relationship (R2> 0.70). The time series N diagnosis curves established by critical NDRE values achieved recognition accuracy of over 89%. The validation accuracy of critical NDRE values achieved 93.84%. The probability of the calculated topdressing rate (N) falling between the agronomic optimal N rate (AONR) and economic optimal N rate (EONR) is 86%.
The time series N diagnosis curve offered possibility to real-time judgement of plant N status. In addition, the subsequent N topdressing design was proved through the improvement of existing sufficiency index (SI) algorithm.
The time series N diagnosis curve will provide valuable decision support for the optimal N fertilizer management of wheat and rice. Moreover, the UAV platform holds promising potential for regional-scale application in the future.
•N fertilizer significantly affected dynamics of N accumulation and canopy spectra.•NDRE had a good correlation with PNA and NNI of wheat and rice.•RAGDD-based time series N diagnosis curve was established and verified.•N diagnosis curve combined well with SINR to guide field topdressing in real time.
•Soil, meteorological, management, and RS data were combined using ML algorithms.•ML models for in-season prediction of yield and reactive N losses were developed.•N damage costs of reactive N losses ...were considered in calculating EONR.•In-season AONR and EONR predicted by RFR and SVR well accorded with observed values.•Historical meteorological data improved accuracy for predicting AONR and EONR.
The modern in-season crop N recommendation approaches should have high reliability in promoting agricultural sustainability. These approaches are relevant to soil properties, meteorological conditions, management practices, and crop in-season growing status. This study aims to use machine learning (ML) algorithms to incorporate the above variables as well as the field reactive nitrogen (N) losses (i.e., N damage cost) simulated by a DeNitrification–DeComposition (DNDC) model to develop a new strategy for optimizing rice in-season topdressing N (TN) usage. Rice field experiments with multiple N treatments and rice varieties were carried out during 2015–2021 at four study sites in eastern China. Four ML algorithms, namely random forest regression (RFR), support vector regression (SVR), lasso regression (LSR), and partial least square regression (PLSR) were used to develop in-season prediction models of yield and reactive N losses by combining soil, meteorological, and management data with crop remote sensing data. The observed in-season agronomic optimum N rates (AONR) that can maximize rice yield at different sites were in the range of 116.5 to 177.4 kg N ha−1, while the in-season economic optimum N rates (EONR) that can maximize marginal revenue (i.e., yield income minus N fertilizer costs and N damage costs) were in the range of 97.4 to 163.6 kg N ha−1. The developed ML models were further used to simulate yield and marginal revenue responses to a series of assumed TN rates (0–300 kg N ha−1, gradient = 20 kg N ha−1). Comparably, RFR model and SVR model were more suitable for determining optimum TN rates, because their simulated response curves of yield and marginal revenue fit the normal regulation (linear plus plateau or single-peak shapes). Independent validation results showed that the in-season AONR and EONR predicted by RFR and SVR well accorded with the observed values (R2 ≥ 0.64, RRMSE ≤ 18.3 %), and the accuracy of ML models containing both historical and in-season meteorological information is superior to ML models that contain in-season meteorological information only. The proposed ML-based strategy is expected to help the regional rice production systems precisely manage N use, improve net profits, and reduce environmental footprints.
Integrating remote sensing (RS)-based variable rate nitrogen (N) recommendation (VRNR) algorithms and management zones (MZs) may improve the accuracy and efficiency of site-specific N management. ...However, its potential benefits for application in commercial rice production systems can hardly be assessed, since it requires to intervene in common agricultural practices and causes certain economic and environmental consequences. Through a machine learning approach, this study aims to comprehensively evaluate the economic and environmental benefits of applying different N management strategies to a town-scale rice production system. Rice field experiments were conducted during 2017–2021 to establish the sufficiency index-based N recommendation algorithm (SIA). The rice fields at Diaoyu town were classified into 12949 rice N management grids. The historical (2020) and in-season (2021) Sentinel-2 images during rice growing seasons were clustered and overlapped to derive RS-based MZs. Five different in-season N topdressing strategies were used to calculate N topdressing rates for each N management grid in the 2021 rice growing season, including: i 150 kg N ha−1 of uniform N topdressing rate (Nlocal), ii 120 kg N ha−1 of uniform N topdressing rate (Nredu), iii SIA-based N topdressing rate (Nrec1), iv SIA-based N topdressing rate combined with MZs (Nrec2), v average of the recommended N rates of Nrec2 in each MZ (Nrec3). Previously developed random forest models were used to simulate the final yield and field reactive N losses of each grid. Simulation results showed that the Nlocal obtained the highest yield level, while simply reducing 20% N topdressing rate (Nredu) would decrease the net profit (NP). Compared with Nlocal, the Nrec1, Nrec2 and Nrec3 saved N topdressing amounts by 17.9%−22.5%, and reduced N damage cost (NDC) by 6.0%−7.8%; meanwhile, NP, N recovery efficiency (NRE), and partial factor productivity of N fertilizer (PFPN) were increased by 2.3%−3.0%, 4.9%−6.0%, and 10.6%−14.3%, respectively. Comparably, the performance of Nrec2 was the optimum among the three VRNR approaches. Overall, through the synthetical evaluation of different N topdressing scenarios, this study demonstrated that combining VRNR algorithm and RS-derived MZs may help regional rice production systems achieve higher N utilization efficiency and economic benefits, along with lower environmental risks.
Display omitted
•Historical and in-season images were used to identify rice management zones (MZs).•Uniform and variable rate nitrogen management (VRN) strategies were constructed.•Machine-learning model was used to predict agronomic and environmental indicators.•VRN algorithm combined with MZ can better reduce N losses and improve net profit.
Phosphorus‐doped hexagonal tubular carbon nitride (P‐TCN) with the layered stacking structure was obtained from a hexagonal rod‐like single crystal supramolecular precursor (monoclinic, C2/m). The ...production process of P‐TCN involves two steps: 1) the precursor was prepared by self‐assembly of melamine with cyanuric acid from in situ hydrolysis of melamine under phosphorous acid‐assisted hydrothermal conditions; 2) the pyrolysis was initiated at the center of precursor under heating, thus giving the hexagonal P‐TCN. The tubular structure favors the enhancement of light scattering and active sites. Meanwhile, the introduction of phosphorus leads to a narrow band gap and increased electric conductivity. Thus, the P‐TCN exhibited a high hydrogen evolution rate of 67 μmol h−1 (0.1 g catalyst, λ >420 nm) in the presence of sacrificial agents, and an apparent quantum efficiency of 5.68 % at 420 nm, which is better than most of bulk g‐C3N4 reported.
Phosphorus‐doped hexagonal carbon nitride tubes were obtained from a rod‐like supramolecular precursor through phosphorous acid assisted hydrothermal and subsequent thermal treatment. It exhibits a high visible‐light photocatalytic hydrogen evolution performance that is better than most reported bulk carbon nitrides, which is due to the hierarchical micro‐nanostructure and P doping.