Remote predictions of the nitrogen nutrition index (NNI) are useful for precise nitrogen (N) management in the field. Several studies have recommended two methods for estimating the NNI, which are classified as mechanistic and semi-empirical methods in this study. However, no studies have been conducted to thoroughly analyze and compare these two methods. Using winter wheat as an example, this study compared the performances of these two methods for estimating the NNI to determine which method is more suitable for practical use. Field measurements were conducted to determine the above ground biomass, N concentration and canopy spectra during different wheat growth stages in 2012. Nearly 120 samples of data were collected and divided into different calibration and validation datasets (containing data from single or multi-growth stages). Based on the above datasets, the performances of the two NNI estimation methods were compared, and the influences of phenology on the methods were analyzed. All models that used the mechanistic method with different calibration datasets performed well when validated by validation datasets containing single growth or multi-growth stage data. The validation results had R2 values between 0.82 and 0.94, root mean square error (RMSE) values between 0.05 and 0.17, and RMSE% values between 5.10% and 14.41%. Phenology had no effect on this type of NNI estimation method. However, the semi-empirical method was influenced by phenology. The performances of the models established using this method were determined by the type of data used for calibration. Thus, the mechanistic method is recommended as a better method for estimating the NNI. By combining proper N management strategies, itcan be used for precise N management.
1 January 2019 in Journal of Global Change Data & Discovery
To prevent potentially unsuitable activities during vegetation restoration, it is important to examine the impact of historical restoration activities on the target ecological system to inform future restoration policies. Taking the Loess Plateau of China as an example, a regionalization method and corresponding scheme were proposed to select suitable vegetation types (forested lands, woody grasslands/bushlands, grasslands, or xerophytic shrublands and semi-shrublands) for a given location using remote sensing technology in order to analyze the vegetation growth status before and after the largest ecological conservation project in the country: The Grain for Green Program (GTGP). To design the scheme, remote sensing data covering the periods before and after the implementation of the GTGP (the 1980s and 2001–2013) were collected, along with soil, meteorological, and topographic data. The net primary production (NPP) values for 2001–2013 were calculated using the Carnegie-Ames-Stanford Approach (CASA) model. Locations representing the native vegetation and the restored vegetation were first recognized using maps of vegetation cover. Then, for the restored vegetation area, the places suitable for planting the covered vegetation type were selected by comparing the NPP value of the corresponding vegetation type in the native vegetation area to the NPP value in the site under consideration. Third, half of these sites were uniformly selected based on their NPP value, and these areas and the native vegetation area were used as training regions. Based on weather, soil, and topographic data, a new regionalization scheme was designed using standardized Euclidean distances. Finally, data from the remainder of the Loess Plateau were used to validate the new regionalization scheme, which was also compared to an existing Chinese eco-geographical regionalization scheme. The results showed that the new regionalization scheme performed well, with an average potential classification accuracy of 81.81%. Compared with the eco-geographical regionalization scheme, the new scheme exhibited improved the consistency of vegetation dynamics, reflecting the potential to better guide vegetation restoration activities on the Loess Plateau.
Crop row detection using unmanned aerial vehicle (UAV) images is very helpful for precision agriculture, enabling one to delineate site-specific management zones and to perform precision weeding. For crop row detection in UAV images, the commonly used Hough transform-based method is not sufficiently accurate. Thus, the purpose of this study is to design a new method for crop row detection in orthomosaic UAV images. For this purpose, nitrogen field experiments involving cotton and nitrogen and water field experiments involving wheat were conducted to create different scenarios for crop rows. During the peak square growth stage of cotton and the jointing growth stage of wheat, multispectral UAV images were acquired. Based on these data, a new crop detection method based on least squares fitting was proposed and compared with a Hough transform-based method that uses the same strategy to preprocess images. The crop row detection accuracy (CRDA) was used to evaluate the performance of the different methods. The results showed that the newly proposed method had CRDA values between 0.99 and 1.00 for different nitrogen levels of cotton and CRDA values between 0.66 and 0.82 for different nitrogen and water levels of wheat. In contrast, the Hough transform method had CRDA values between 0.93 and 0.98 for different nitrogen levels of cotton and CRDA values between 0.31 and 0.53 for different nitrogen and water levels of wheat. Thus, the newly proposed method outperforms the Hough transform method. An effective tool for crop row detection using orthomosaic UAV images is proposed herein.
Gaussian process regression (GPR) can effectively solve the problem of high-dimensional modeling with a small sample size. However, there is a lack of studies comparing GPR with other methods for leaf area index (LAI) inversion using hyperspectral data. In this study, winter wheat was used as the research material to evaluate performance of different methods for LAI inversion, i.e., GPR, an artificial neural network (ANN), partial least squares regression (PLSR) and the spectral index (SI). To this end, a 2-year water and nitrogen coupled experiment was conducted, and canopy hyperspectral and LAI data were measured at the critical growth stages of wheat. Based on these data, calibration and validation datasets were obtained, and the LAI prediction model was constructed using the above four methods and validated. The results showed that the LAI inversion models of the SI were the least effective compared with other methods, with R2 and RMSE ranging from 0.42–0.76 and 0.80–1.04 during calibration and R2 and RMSE ranging from 0.37–0.55 and 0.94–1.09 during validation. The ANN and GPR had the best results, with R2 of 0.89 and 0.85 and RMSE of 0.46 and 0.53 during calibration and R2 of 0.74 and 0.71 and RMSE of both 0.74 during validation. The PLSR had intermediate LAI inversion results, with R2 and RMSE values of 0.80 and 0.61 during calibration and R2 and RMSE values of 0.67 and 0.80 during validation. Thus, the ANN and GPR methods were recommended for LAI inversion of winter wheat.
Predicting leaf nitrogen content (LNC) using unmanned aerial vehicle (UAV) images is of great significance. Traditional LNC prediction methods based on empirical and mechanistic models have limitations. This study aimed to propose a new LNC prediction method based on combining deep learning methods and mechanistic models. Wheat field experiments were conducted to make plants with different LNC values. The LNC and UAV hyperspectral images were collected during the critical growth stages of wheat. Based on these data, a method combining the deep multitask learning method and the N-based PROSAIL model was proposed and compared with traditional LNC prediction methods, including spectral index (SI), partial least squares regression (PLSR) and artificial neural network (ANN) methods. The results show that the new proposed method obtained the best LNC prediction results, with R2, RMSE and RMSE% values of 0.79, 20.86 μg/cm2 and 18.63%, respectively, during calibration and 0.82, 18.40 μg/cm2 and 16.92%, respectively, during validation. The other methods obtained R2, RMSE and RMSE% values between 0.29 and 0.68, 25.71 and 38.52 μg/cm2 and 22.95 and 34.39%, respectively, during calibration and between 0.43 and 0.74, 22.79 and 33.55 μg/cm2 and 20.96 and 30.86%, respectively, during validation. Thus, this study provides an accurate LNC prediction tool for precise nitrogen (N) management in the field.