Yingying Dong

Partial Least Square Discriminant Analysis Based on Normalized Two-Stage Vegetation Indices for Mapping Damage from Rice Diseases Using PlanetScope Datasets

In recent decades, rice disease co-epidemics have caused tremendous damage to crop production in both China and Southeast Asia. A variety of remote sensing based approaches have been developed and applied to map diseases distribution using coarse- to moderate-resolution imagery. However, the detection and discrimination of various disease species infecting rice were seldom assessed using high spatial resolution data. The aims of this study were (1) to develop a set of normalized two-stage vegetation indices (VIs) for characterizing the progressive development of different diseases with rice; (2) to explore the performance of combined normalized two-stage VIs in partial least square discriminant analysis (PLS-DA); and (3) to map and evaluate the damage caused by rice diseases at fine spatial scales, for the first time using bi-temporal, high spatial resolution imagery from PlanetScope datasets at a 3 m spatial resolution. Our findings suggest that the primary biophysical parameters caused by different disease (e.g., changes in leaf area, pigment contents, or canopy morphology) can be captured using combined normalized two-stage VIs. PLS-DA was able to classify rice diseases at a sub-field scale, with an overall accuracy of 75.62% and a Kappa value of 0.47. The approach was successfully applied during a typical co-epidemic outbreak of rice dwarf (Rice dwarf virus, RDV), rice blast (Magnaporthe oryzae), and glume blight (Phyllosticta glumarum) in Guangxi Province, China. Furthermore, our approach highlighted the feasibility of the method in capturing heterogeneous disease patterns at fine spatial scales over the large spatial extents.

Estimating Winter Wheat Leaf Area Index From Ground and Hyperspectral Observations Using Vegetation Indices

Growing numbers of studies have focused on evaluating the ability of vegetation indices (VIs) to predict biophysical parameters such as leaf area index (LAI) and chlorophyll. In this study, empirical models were used to estimate winter wheat LAI based on three spectral indices [the normalized difference vegetation index (NDVI), the modified simple ratio index (MSR), and the modified soil-adjusted vegetation index (MSAVI)], and three band-selection approaches (the conventional approach, the red edge approach, and the best correlated approach), which were used to calculate VIs. The aim was to enhance the relationships between the indices and LAI values by improving the band-selection approaches so as to produce a suitable VI for winter wheat LAI estimation. Using hyperspectral airborne data and ground-measured spectra as well as ground LAI measurements collected during two field campaigns, winter wheat LAIs were estimated and validated using different VIs calculated by different band combinations. Our results showed that the MSAVI provided the best LAI estimations when using ground measured spectra with R2 over 0.74 and RMSE less than 0.98. The NDVI provided the most robust estimation results across different sites, years, and sensors, although it was not adequate for LAI estimation of moderately dense canopies due to the saturation that occurred when LAI ) 3. The MSR demonstrated more severe scattering and lower predictive accuracy than the NDVI and, therefore, was not a perfect solution to the saturation issue. In addition, it was also shown that the best correlated approach improved the predictive power of the indices and revealed the importance of red edge bands for LAI estimation; meanwhile, the red edge approach (based on the reflectance at 705 and 750 nm) was not always superior to the conventional approach (based on the reflectance at 670 and 800 nm). The results were promising and should facilitate the use of VIs in crop LAI measurements.

Integrating Early Growth Information to Monitor Winter Wheat Powdery Mildew Using Multi-Temporal Landsat-8 Imagery

Powdery mildew is one of the dominant diseases in winter wheat. The accurate monitoring of powdery mildew is important for crop management and production. Satellite-based remote sensing monitoring has been proven as an efficient tool for regional disease detection and monitoring. However, the information provided by single-date satellite scene is hard to achieve acceptable accuracy for powdery mildew disease, and incorporation of early period contextual information of winter wheat can improve this situation. In this study, a multi-temporal satellite data based powdery mildew detecting approach had been developed for regional disease mapping. Firstly, the Lansat-8 scenes that covered six winter wheat growth periods (expressed in chronological order as periods 1 to 6) were collected to calculate typical vegetation indices (VIs), which include disease water stress index (DSWI), optimized soil adjusted vegetation index (OSAVI), shortwave infrared water stress index (SIWSI), and triangular vegetation index (TVI). A multi-temporal VIs-based k-nearest neighbors (KNN) approach was then developed to produce the regional disease distribution. Meanwhile, a backward stepwise elimination method was used to confirm the optimal multi-temporal combination for KNN monitoring model. A classification and regression tree (CART) and back propagation neural networks (BPNN) approaches were used for comparison and validation of initial results. VIs of all periods except 1 and 3 provided the best multi-temporal data set for winter wheat powdery mildew monitoring. Compared with the traditional single-date (period 6) image, the multi-temporal images based KNN approach provided more disease information during the disease development, and had an accuracy of 84.6%. Meanwhile, the accuracy of the proposed approach had 11.5% and 3.8% higher than the multi-temporal images-based CART and BPNN models’, respectively. These results suggest that the use of satellite images for early critical disease infection periods is essential for improving the accuracy of monitoring models. Additionally, satellite imagery also assists in monitoring powdery mildew in late wheat growth periods.

Wavelet-Based Rust Spectral Feature Set (WRSFs): A Novel Spectral Feature Set Based on Continuous Wavelet Transformation for Tracking Progressive Host–Pathogen Interaction of Yellow Rust on Wheat

Understanding the progression of host–pathogen interaction through time by hyperspectral features is vital for tracking yellow rust (Puccinia striiformis) development, one of the major diseases of wheat. However, well-designed features are still open issues that impact the performance of relevant models to nondestructively detect pathological progress of wheat rust. The aim of this paper is (1) to propose a novel wavelet-based rust spectral feature set (WRSFs) to uncover wheat rust-related processes; and (2) to evaluate the performance and robustness of the proposed WRSFs and models for retrieving the progression of host–pathogen interaction and tracking rust development. A hyperspectral dataset was collected by analytical spectral devices (ASD) spectroradiometer and Headwall spectrograph, along with corresponding physiological measurements of chlorophyll index (CHL), nitrogen balance index (NBI), anthocyanin index (ANTH), and percentile dry matter (PDM) from the 7th to 41st day after inoculation (dai) under controlled conditions. The resultant findings suggest that the progression of yellow rust on wheat is better characterized by the proposed WRSFs (R2 > 0.7). The WRSFs-based PLSR model provides insight into specific leaf biophysical variations in the rust pathological progress. To evaluate the efficiency of the proposed WRSFs on yellow rust discrimination during different infestation stages, the identified WRSFs and vegetation indices (VIs) were fed into linear discriminant analysis (LDA) and support vector machine (SVM) classification frames. The WRSFs in conjunction with a SVM classifier can obtain better performance than that of LDA method and the VIs-based models. Overall, synthesizing the biophysical analysis, retrieving accuracy, and classification performance, we recommend the proposed WRSFs for monitoring the progression of the host–pathogen interaction of yellow rust on wheat cross various hyperspectral sensors.

The influence of landscape's dynamics on the Oriental Migratory Locust habitat change based on the time-series satellite data

Landscape structure and vegetation coverage are important habitat conditions for Oriental Migratory Locust infestation in East Asia. Characterizing the landscapes dynamics of locust habitat is meaningful for reducing the occupation of locusts and limiting potential risks. To better understand causes and consequences of landscape pattern and locust habitat, it is not enough to simply detect locust habitat of each year. Rather, landcover transitions causing the change of locust habitat area must also be explored. This paper proposes an integrated implement to quantify the influence of landscapes dynamics on locust habitat changes based on three tenets: 1) temporal context can provide insight into the land cover transitions, 2) the detection of locust habitat area is operated on patches rather than pixels with full consideration of landscapes ecology, 3) the modeling must be flexible and unsupervised. These ideas have not been previously explored in demonstrating the possible role of changes in landscape characteristics to drive locust habitat transitions. The case study focuses on the Dagang district, a hot spot of locust infestation of China, from 2000 to 2015. Firstly, the seasonal characteristics of typical landcovers in NDVI, TVI, and LST were extracted from fused Landsat-MODIS surface reflectance imagery. Subsequently, a landscape membership-based random forest (LMRF) algorithm was proposed to quantify the landscape structure and hydrological regimen of locust habitat at the patch level. Finally, we investigated the correlations between the specific landcover transitions and habitat changes. Within the 16 years observations, our findings suggest that the sparse reeds and weeds in the vicinity of beach land, riverbanks, and wetlands are the dominant landscape structure associated with locust habitat change (R2 > 0.68), and the fluctuation in the water level is a key ecological factor to facilitate the locust habitat change (R2 > 0.61). These results are instrumental for developing precision pesticide use to reduce environmental degradation, and providing positive perspectives for ecological management and transformation of locust habitats.

Off-Nadir Hyperspectral Sensing for Estimation of Vertical Profile of Leaf Chlorophyll Content within Wheat Canopies

Monitoring the vertical profile of leaf chlorophyll (Chl) content within winter wheat canopies is of significant importance for revealing the real nutritional status of the crop. Information on the vertical profile of Chl content is not accessible to nadir-viewing remote or proximal sensing. Off-nadir or multi-angle sensing would provide effective means to detect leaf Chl content in different vertical layers. However, adequate information on the selection of sensitive spectral bands and spectral index formulas for vertical leaf Chl content estimation is not yet available. In this study, all possible two-band and three-band combinations over spectral bands in normalized difference vegetation index (NDVI)-, simple ratio (SR)- and chlorophyll index (CI)-like types of indices at different viewing angles were calculated and assessed for their capability of estimating leaf Chl for three vertical layers of wheat canopies. The vertical profiles of Chl showed top-down declining trends and the patterns of band combinations sensitive to leaf Chl content varied among different vertical layers. Results indicated that the combinations of green band (520 nm) with NIR bands were efficient in estimating upper leaf Chl content, whereas the red edge (695 nm) paired with NIR bands were dominant in quantifying leaf Chl in the lower layers. Correlations between published spectral indices and all NDVI-, SR- and CI-like types of indices and vertical distribution of Chl content showed that reflectance measured from 50°, 30° and 20° backscattering viewing angles were the most promising to obtain information on leaf Chl in the upper-, middle-, and bottom-layer, respectively. Three types of optimized spectral indices improved the accuracy for vertical leaf Chl content estimation. The optimized three-band CI-like index performed the best in the estimation of vertical distribution of leaf Chl content, with R2 of 0.84–0.69, and RMSE of 5.37–5.56 µg/cm2 from the top to the bottom layers, while the optimized SR-like index was recommended for the bottom Chl estimation due to its simple and universal form. We suggest that it is necessary to take into account the penetration characteristic of the light inside the canopy for different Chl absorption regions of the spectrum and the formula used to derive spectral index when estimating the vertical profile of leaf Chl content using off-nadir hyperspectral data.