Search

It is important to implement detection and assessment of plant diseases based on remotely sensed data for disease monitoring and control. Hyperspectral data of healthy leaves, leaves in incubation period and leaves in diseased period of wheat stripe rust and wheat leaf rust were collected under in-field conditions using a black-paper-based measuring method developed in this study. After data preprocessing, the models to identify the diseases were built using distinguished partial least squares (DPLS) and support vector machine (SVM), and the disease severity inversion models of stripe rust and the disease severity inversion models of leaf rust were built using quantitative partial least squares (QPLS) and support vector regression (SVR). All the models were validated by using leave-one-out cross validation and external validation. The diseases could be discriminated using both distinguished partial least squares and support vector machine with the accuracies of more than 99%. For each wheat rust, disease severity levels were accurately retrieved using both the optimal QPLS models and the optimal SVR models with the coefficients of determination (R2) of more than 0.90 and the root mean square errors (RMSE) of less than 0.15. The results demonstrated that identification and severity evaluation of stripe rust and leaf rust at the leaf level could be implemented based on the hyperspectral data acquired using the developed method. A scientific basis was provided for implementing disease monitoring by using aerial and space remote sensing technologies.

Sorghum is known as a major potential feedstock for biofuel production. Being able to efficiently discover genetic control of many traits over a large number of genotypes, genome-wide association study (GWAS) has become a powerful tool for studying sorghum biomass yield components. However, automated high-throughput field-based plant phenotyping is now the bottleneck for scaling up such experiments. This paper presents an auto-guidance enabled utility tractor which navigates itself between crop rows with a predefined path while collecting stereo images of sorghum samples from both sides of the vehicle. Three levels of stereo camera heads were instrumented to capture images of plants up to 3 meters tall. The stereo images were processed offline to reconstruct 3D point clouds using Semi-Global Block Matching. A semi-automated software interface was developed to measure stem diameter due to the strict sampling strategy and the complexity of high-density crop canopy. An automated hedge-based feature extraction pipeline was proposed to quantify other variations in plant architecture traits such as plant height, leaf area index (LAI) and vegetation volume index (VVI). The stem diameter measured using the semiautomatic method showed high correlation (0.958) to hand measurement.

Crop phenology is essential for evaluating crop production in the food insecure regions of West Africa. The aim of the paper is to study whether satellite observation of plant phenology are consistent with ground knowledge of crop cycles as expressed in agro-simulations. We used phenological variables from a MODIS Land Cover Dynamics (MCD12Q2) product and examined whether they reproduced the spatio-temporal variability of crop phenological stages in Southern Mali. Furthermore, a validated cereal crop growth model for this region, SARRA-H (System for Regional Analysis of Agro-Climatic Risks), provided precise agronomic information. Remotely-sensed green-up, maturity, senescence and dormancy MODIS dates were extracted for areas previously identified as crops and were compared with simulated leaf area indices (LAI) temporal profiles generated using the SARRA-H crop model, which considered the main cropping practices. We studied both spatial (eight sites throughout South Mali during 2007) and temporal (two sites from 2002 to 2008) differences between simulated crop cycles and determined how the differences were indicated in satellite-derived phenometrics. The spatial comparison of the phenological indicator observations and simulations showed mainly that (i) the satellite-derived start-of-season (SOS) was detected approximately 30 days before the model-derived SOS; and (ii) the satellite-derived end-of-season (EOS) was typically detected 40 days after the model-derived EOS. Studying the inter-annual difference, we verified that the mean bias was globally consistent for different climatic conditions. Therefore, the land cover dynamics derived from the MODIS time series can reproduce the spatial and temporal variability of different start-of-season and end-of-season crop species. In particular, we recommend simultaneously using start-of-season phenometrics with crop models for yield forecasting to complement commonly used climate data and provide a better estimate of vegetation phenological changes that integrate rainfall variability, land cover diversity, and the main farmer practices.

In recent years, within the European Union several legislative, monitoring and coordinating actions have been undertaken to encourage sustainable use of resources, reduction in the use of chemicals and improvement of the urban environment. In this respect, two concepts that are strictly related to most of the aspects above are: “precision agriculture” and “precision conservation” and more specifically “precision turfgrass management.” Optical sensing has become a crucial part of precision turfgrass management and spectral reflectance in particular has been an active area of research for many years. However, while turfgrass status evaluation by proximity-sensed spectral reflectance appears to be an established and reliable practice, much more could be achieved in terms of monitoring of large turfgrass areas through remote sensing, and in particular through satellite imagery. This paper reports the results of a trial attempting to evaluate the spectral signatures of several turfgrass species and cultivars, for future use in turfgrass satellite monitoring. Our experimental study focused on 20 turfgrass species/varieties including perennial ryegrasses, tall fescues, kentucky bluegrasses, bermudagrass ecotypes, seeded commercial bermudagrasses, vegetatively propagated bermudagrasses, Zoysia japonica and non-japonica zoysiagrasses. Various biological and agronomical parameters were studied and turfgrass spectral reflectance for all entries was gathered. Vegetation indices were calculated by simulating the available wavelengths deriving from World View 2 satellite imagery. Results showed that within the same species selected vegetation indices are often able to discriminate between different varieties that have been established and maintained with identical agronomical practices.

We have developed an image analysis system for mapping white clover pastures. The information from digital colour photographs is processed by software (Trifolium.exe) specially designed for the purpose. The software estimates the coverage of clover, weeds and bare ground, and the unidentified remainder of the total area is regarded as covered by grass. To evaluate the reliability of the estimates of clover content, the clover on paper printouts of non-processed images were marked manually and analysed by a photo scanner and commercially available software. The outputs from Trifolium.exe and the estimates from scanned manual markings were highly correlated (r 2=0.81). A sensitivity test was conducted to quantify the impact of changes of six user-adjustable parameters of Trifolium.exe. The software output of clover coverage was sensitive for changes in three, soil coverage for changes in one, and weed coverage for changes in all parameters. The fact that the digital image acquisition and analysis produce ne...

This paper compares of pixel- and object-based techniques for mapping wild oat weed patches in wheatfields using multi-spectral QuickBird satellite imagery for site-specific weed management. The researchwas conducted at two levels: (1) at the field level, on 11 and 15 individual infested wheat fields in 2006 and2008, respectively, and (2) on a broader level, by analysing the entire 2006 and 2008 images. To evaluatethe wild oat patches mapping at the field level, both pixel- and object-based image analyses were testedwith six classification algorithms: Parallelepipeds (P), Mahalanobis Distance (MD), Maximum Likelihood(ML), Spectral Angle Mapper (SAM), Support Vector Machine (SVM) and Decision Tree (DT). The resultsshowed that weed patches could be accurately detected with both analyses obtaining global accuraciesbetween 80% and 99% for most of the fields. The MD and SVM classifiers were the most accurate forboth the pixel- and object-based images from 2006 and 2008, respectively. In the broad-scale analysis,all of the wheat fields were identified in the imagery using a multiresolution hierarchical segmentationbased on two scales. The first segmentation scale was classified using the MD and ML algorithms todiscriminate wheat fields from other land uses. Accuracies greater than 85% were obtained for MD and88% for ML for both imagery. A hierarchical analysis was then performed with the second segmentationscale, increasing the accuracies to 93% and 91% for 2006 and 2008 imagery, respectively. Finally, based onthe most accurate results obtained in the field-level study, pixel-based classifications using the MD, MLand SVM algorithms were applied to the wheat fields identified. The results of these broad-level analysesshowed that wild oat patches were accurately discriminated in all the wheat fields present in the entireimages with accuracies greater than 91% for all the classifiers tested., This work was partially financed by the Spanish Ministry of Science and Innovation through projects AGL2008-04670-CO3-03 and AGL2011-30442-CO2-01 (FEDER). JAE-Doc CSIC FEDER Program financed the work of J.M. Pena.

Rotylenchulus reniformis nematodes present in the soil are one of the major nematode parasite species significantly affecting the growth and development of cotton plants. Recent studies have shown that the nematode numbers in the plant's rhizosphere has direct impact on the reflectance of the plants. In this paper, authors utilize this correlation in developing a field worthy methodology for predicting nematode population number extant in the plant's rhizosphere from variable plant's reflectance. To accomplish this task, a supervised Self-organized map (SOM) was trained using the hyperspectral data signatures of cotton plants affected by different known nematode numbers. The hyperspectral signatures used for training were collected from the cotton plants grown in controlled environment. Twelve field samples (uncontrolled environment) with known nematode numbers obtained from lab analysis of the soil were presented to the supervised trained Self-Organized Map. The location of the sample on the labeled supervised-SOM was used to determine the estimated nematode population of the field sample. In addition to the map grid, the locations of the samples were also visualized using U-matrix, to determine whether the samples were not corrupt or located in the junk part of the map. In addition to the primary goal, hyperspectral signatures of both training and testing data were divided into three sub-regions: Visible region, NIR region and Mid-IR region to observe whether any particular region was the most effective in predicting nematode population.

Bidens pilosa L. (commonly known as cobbler's peg) is an annual broad leaf weed widely distributed in tropical and subtropical regions of the world and is reported to be a weed of 31 crops, including wheat. Automatic detection of Bidens in wheat farms is a non-trivial problem due to their similarity in colour and presence of occlusions. This paper proposes a methodology which could be used to discriminate Bidens from wheat to be used in operations such as autonomous weed destruction. A spectrometer is used to analyse the optical properties of Bidens and wheat leaves while achieving high classification results. However, due to the practical constraints of using spectrometers, a colour camera-based technique is proposed. It is shown that the colour-based segmentation followed by shape-based validation algorithm gives rise to high detection rates with lower false detections. We have experimentally evaluated the algorithm with Bidens detection rate of 80% and a false alarm rate of 10%.