Optimizing chickpea yield prediction under wilt disease through synergistic integration of biophysical and image parameters using machine learning models

BackgroundThe EuroQoL 5D (EQ-5D) has been widely used in studies of cardiac disease, but its measurement properties in this group are not well established. The study aimed to quantify the relationship between measures commonly used in studies of cardiac disease and the EQ-5D index across different levels of disease severity.MethodsPatient-level data from 7 studies of cardiac interventions were used, which included randomised trials and observational studies. Relationships between the EQ-5D index and commonly used cardiac measures, Canadian Cardiovascular Society (CCS) angina severity class, treadmill exercise time (ETT) and scales of the Seattle Angina Questionnaire (SAQ) were examined. Mixed effects linear regression was used to assess these relationships, with the EQ-5D index as the response.ResultsStudy sample sizes ranged from 68 to 2419. Mean baseline EQ-5D index ranged from 0.77 in patients at diagnosis (95% CI 0.75, 0.78) to 0.43 in patients with advanced disease (95% CI 0.39, 0.48) and differed significantly across studies (p < 0.001). There was evidence of a ceiling effect in patients at diagnosis. The minimum clinically important difference of a one minute increase in ETT was associated with a 0.019 (95% CI 0.014, 0.025) increase in EQ-5D index. One class increase in CCS was associated with a 0.11 (95% CI 0.09, 0.13) decrease in EQ-5D index. A 10 unit increase in SAQ scales was associated with increases between 0.04 and 0.07 in EQ-5D index (95% CIs 0.03, 0.05 and 0.05, 0.08). Tests of heterogeneity indicated the EQ-5D-covariate relationships were consistent across levels of disease severity for ETT and the treatment satisfaction scale of the SAQ, but heterogeneous for age, gender, CCS angina class and other scales of the SAQ.ConclusionThe EQ-5D index varies with coronary disease severity. The relationship between the EQ-5D index and an outcome measure used in cardiac intervention studies, ETT, was consistent across disease severity levels, but the relationship between demographic variables, CCS angina class and most of the SAQ scales and the EQ-5D index was heterogeneous for patients with different levels of coronary disease. Differences in the EQ-5D index associated with clinically important differences in cardiac measures can be quantified and vary between three important examples - angina class, ETT and SAQ.

Introduction: Water shortage is the most important factor affecting crop production in the world. The deficit irrigation is a way to reduce water consumption in farming. The Partial Root- zone Drying (PRD) irrigation is a new improvement in deficit irrigation in which the half of the root zone is irrigated alternatively in scheduled irrigation events. In the fixed partial root zone drying (FPRD) the irrigation is fixed to one side of the root zone in the growing season. Maize is a drought sensitive crop. In maize, secondary traits related to drought resistance are considered in producing tolerate cultivars. Materials and Methods: An experiment was conducted in order to investigate the effects of regulated deficit irrigation, variable partial root zone drying (PRD) and fixed partial root zone drying (FPRD) on the yield, physiological and photosynthetic parameters of forage maize (KSC 704) during the growing seasons of 2014 in Mashhad region. A factorial experiment based on randomized complete block design with four replications was carried out. The treatments included the full irrigation (FI) and the deficit irrigations (regulated deficit irrigation (DI) and the replacements of 80 % (DI80) and 60 % (DI60) of total water requirement, fixed PRD (FPRD) at 100% (FPRD100), 80% (FPRD80) and 60%(FPRD60) of water requirement, and variable PRD at 100% (PRD100), 80% (PRD80) and 60% (PRD60) of water requirement). Drip irrigation tapes were placed between plant rows. In the full irrigation and regulated deficit irrigation treatments, the plants were irrigated from two sides for every irrigation. In the PRD, one of two neighboring tapes was alternatively used for irrigation. In FPRD, a drip tape was used for two plant rows and irrigation was fixed to one side of the root. The irrigation interval was 3 days for all treatments. Dry and fresh forage yield, leaf area index (LAI), stomatal conductance, leaf relative water content (RWC) and chlorophyll content were measured. Results and Discussions: All the measured traits were affected by the deficit irrigation. The highest fresh forage yield (72099 kg/ha) was produced by the full irrigation treatment. The statistical comparison showed that there was no significant difference between regulated deficit irrigation and PRD method for the fresh forage yield. But the FPRD treatment reduced the fresh forage yield. There was no significant difference between the fresh forage yield of FI and PRD80 treatments. The dry forage yield was affected by the different irrigation methods, irrigation levels and the interaction effects of the treatments (p

Accurate leaf area index estimation in sorghum using high-resolution UAV data and machine learning models

Current vegetation indices and biophysical parameters derived from optical satellite data for forest monitoring are widely used in various applications but can be limited by atmospheric effects like clouds. Synthetic aperture radar (SAR) data can offer insightful and systematic forest monitoring with complete time series due to signal penetration through clouds and day and night image acquisitions. This study explores the use of SAR data, combined with ancillary data and machine learning (ML), to estimate forest parameters typically derived from optical satellites. It investigates whether SAR signals provide sufficient information for the accurate estimation of these parameters, focusing on two spectral vegetation indices (Normalized Difference Vegetation Index – NDVI and Enhanced Vegetation Index – EVI) and two biophysical parameters (Leaf Area Index – LAI and Fraction of Absorbed Photosynthetically Active Radiation – FAPAR) in healthy and disturbed temperate forests in Czechia and Central Europe in 2021. Vegetation metrics derived from Sentinel-2 multispectral data were used to evaluate the results. A paired multi-modal time-series dataset was created using Google Earth Engine (GEE), including temporally and spatially aligned Sentinel-1, Sentinel-2, DEM-based features and meteorological variables, along with a forest type class. The inclusion of DEM-based auxiliary features and additional meteorological information improved the results. In the comparison of ML models, the traditional ML algorithms, Random Forest Regressor and Extreme Gradient Boosting (XGB) slightly outperformed the Automatic Machine Learning (AutoML) approach, auto-sklearn, for all forest parameters, achieving high accuracies (R2 between 70% and 86%) and low errors (0.055–0.29 of mean absolute error). XGB was the most computationally efficient. Moreover, SAR-based estimations over Central Europe achieved comparable results to those obtained in testing within Czechia, demonstrating their transferability for large-scale modeling. A key advantage of the SAR-based vegetation metrics is the ability to detect abrupt forest changes with sub-weekly temporal accuracy, providing up to 240 measurements per year at a 20 m resolution.

Unmanned Aerial System (UAS)-based phenotyping of soybean using multi-sensor data fusion and extreme learning machine

This study proposes a new method for inverting radiative transfer models to retrieve canopy biophysical parameters using remote sensing imagery. The inversion procedure is improved with respect to standard inversion, and achieves simultaneous inversion of leaf area index (LAI), soil reflectance (ρsoil), chlorophyll content (Ca+b) and average leaf angle (ALA). In this approach, LAI is used to constrain modelling conditions during the inversion process, providing information about the phenological state of each plot under study. Due to the small area of the vegetation plots used for the inversion procedure and in order to avoid redundant information and improve computation efficiency, existing plot segmentation was used. All retrieved biophysical parameters, except LAI, were assumed to be invariant within each plot. The proposed methodology, based on the combination of PROSPECT and SAILH models, was tested over 16 cereal fields and 51 plots, on two dates, which were chosen to ensure crop assessment at different phenological stages. Plots were selected to provide a wide range of LAI between 0 and 6. Field measurements of LAI, ALA and Ca+b were conducted and used as ground truth for validation of the proposed model-inversion methodology. The approach was applied to very high spatial resolution remote sensing data from the QuickBird 2 satellite. The inversion procedure was successfully applied to the imagery and retrieved LAI with R 2 = 0.83 and RMSE = 0.63 when compared to LAI2000 ground measurements. Separate inversions for barley and wheat yielded R 2 = 0.89 (RMSE = 0.64) and R 2 = 0.56 (RMSE = 0.61), respectively.

Machine learning models perform better than traditional empirical models for stomatal conductance when applied to multiple tree species across different forest biomes

Inversion of radiative transfer models (RTM) using a lookup-table (LUT) approach against satellite reflectance data can lead to concurrent retrievals of biophysical parameters such as leaf chlorophyll content (Chl) and leaf area index (LAI), but optimization strategies are not consolidated yet. ESA's upcoming satellites Sentinel-2 (S2) and Sentinel-3 (S3) aim to ensure continuity of old generation satellite sensors by providing superspectral images of high spatial and temporal resolution. This unprecedented data availability leads to an urgent need for developing robust, accurate, and operational retrieval methods. For three simulated Sentinel settings (S2-10 m: 4 bands, S2-20 m: 8 bands and S3-OLCI: 19 bands) various optimization strategies in LUT-based RTM inversion have been evaluated, being the role of i) added noise, ii) multiple best solutions, iii) combined parameters (Chl ×LAI), and iv) applied cost functions. By inverting the PROSAIL model and using data from the ESA-led field campaign SPARC (Barrax, Spain), it was demonstrated that introducing noise and opting for multiple best solutions in the inversion considerably improved retrievals. However, the widely used RMSE was not the best performing cost function. Three families of alternative cost functions were applied here: information measures, minimum contrast, and M-estimates. We found that so-called “Power divergence measure”, “Trigonometric”, and spectral measure with “Contrast function K(x) = -log(x) + x”, yielded more accurate results, although this also depended on the biophysical parameter. Particularly, when simultaneous retrieval of multiple biophysical parameters is the objective then “Contrast function K(x) = -log(x) + x” provided most consistent optimized estimates of leaf Chl, LAI and canopy Chl across the different Sentinel configurations (relative RMSE: 24-29 %).

&lt;abstract&gt; &lt;p&gt;The unmanned aerial vehicle (UAV), as a remote sensing platform, has attracted many researchers in precision agriculture because of its operational flexibility and capability of producing high spatial and temporal resolution images of agricultural fields. This study proposed machine learning (ML) models and their ensembles for peanut yield prediction using UAV multispectral data. We utilized five bands (red, green, blue, near-infra-red (NIR) and red-edge) multispectral images acquired at various growth stages of peanuts using UAV. The correlation between spectral bands and yield was analyzed for each growth stage, which showed that the maturity stages had a significant correlation between peanut yield and spectral bands: red, green, NIR and red edge (REDE). Using these four bands spectral data, we assessed the potential for peanut yield prediction using multiple linear regression and seven non-linear ML models whose hyperparameters were optimized using simulated annealing (SA). The best three ML models, random forest (RF), support vector machine (SVM) and XGBoost, were then selected to construct a cooperative yield prediction framework with both the best ML model and the ensemble scheme from the best three as comparable recommendations to the farmers.&lt;/p&gt; &lt;/abstract&gt;

Sentinel-2 spectral configurations, S2-10m and S2-20m, were evaluated for retrieving essential crop biophysical and biochemical parameters and their effect on the performance of three machine learning regression algorithms (MLRAs) in two African semi-arid sites. The results were benchmarked against all spectral bands (S2-All). The results show that the S2-20m was more robust in retrieving Leaf Area Index (LAI) (RMSE cv : 0.58 m2 m−2, 0.47 m2 m−2), while the S2-10m provided optimal retrievals Leaf Chlorophyll a + b (LC ab ) (RMSE cv : 6.89 µg cm−2, 7.02 µg cm−2) for the two sites, respectively. In contrast, S2-20m performed better in retrieving Canopy Chlorophyll Content (CCC) in Bothaville to an RMSE cv of 35.65 µg cm−2, while S2-10m yielded relatively lower uncertainties (RMSE cv of 26.84 µg cm−2) in Harrismith. Moreover, various MLRAs were sensitive to the various spectral configurations, and performance varied by site. GPR and XGBoost were more robust, and thus have the most potential for crop biophysical and biochemical parameter retrieval in both sites. Based on the benchmark results, the two configurations can be used independently. The results obtained here are relevant for the rapid development of essential crop biophysical and biochemical parameters for precision agriculture using Sentinel-2’s 10 m or 20 m bands, without the need for resampling.

A field experiment was conducted at Agriculture Research station, SKRAU, Bikaner, India during two consecutive kharif seasons to study the effect of tillage practices on growth, yield, economics and stress indicators of pearl millet [Pennisetum glaucum (L.) R. Br.] cultivars under rainfed conditions.The experiment was laid out in split plot design with four tillage practices in main plots (conventional tillage, zero tillage, conventional tillage + ridging and zero tillage + ridging) and four cultivars of pearl millet in sub plots (Pusa composite 443, CZP 9802, MPMH 17 and RHB 177) and replicated four times.Results, pooled over two years, indicated that the tillage practices significantly improved the performance of pearl millet crop.Conventional tillage and zero tillage along with ridging significantly increased the relative leaf water content, proline content and membrane stability index which resulted in higher grain yield, net returns and B:C ratio.Pearl millet cultivars also showed significant variations among the observed parameters.Pusa Composite 443 recorded maximum plant height (138.2 cm) and dry matter accumulation (19.9 g/plant) and remained significantly higher in comparison to pearl millet hybrids (MPMH 17 and RHB 177).Contrary to this, pearl millet hybrids (MPMH 17 and RHB 177) recorded significantly higher grain yield, net return, B:C ratio, relative leaf water content, proline content and membrane stability index in comparison to composite cultivars.Hybrid MPMH 17 gave the highest net return of 21682 under conventional tillage + ridging treatment and remained at par where cv.MPMH 17 or RHB 177 when grown under zero tillage + ridging.

Leaf area index (LAI) products retrieved from observations acquired on one occasion have obvious discontinuity in the time series owing to cloud coverage and other factors, and the accuracy may not meet the needs of many applications. Effectively utilizing data assimilation techniques to retrieve biophysical parameters from the time series of remote-sensing data has attracted special interest. The data assimilation technique is based on a reasonable consideration of dynamic change rules of biophysical parameters and time series observational quantities, thereby improving the quality of retrieved profiles. In this article, a variational assimilation procedure for retrieving LAI from the time series of remote-sensing data is developed. The procedure is based on the formulation of an objective function. A dynamic model is constructed based on the climatology from multi-year Moderate Resolution Imaging Spectroradiometer (MODIS) LAI data to evolve LAI in time, and a radiative transfer model is coupled with the dynamic model to simulate a time series of surface reflectances. A shuffled complex evolution method (developed at the University of Arizona; SCE-UA) optimization algorithm is then used to minimize the objective function and estimate the dynamic model states and the parameters of the coupled model from the MODIS reflectance data with a higher quality in a given time window. The variational assimilation method is applied to the MODIS surface reflectance data for the whole of 2008 at the Heihe river basin to produce regional LAI mapping results. The ground LAI data measured in situ are used to develop algorithms to estimate LAI from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) surface reflectance, and ASTER LAI maps are produced for each ASTER scene using the algorithms developed. Then the ASTER LAI maps are aggregated to compare with the new LAI products. It is found that the variational assimilation method is able to produce temporal continuous LAI products and that accuracy has been improved over the MODIS LAI standard product.

Silicon (Si) has beneficial effect on crop growth and development under water stress condition. The study about the effect of silicon application on growth and water relation of wheat under water-limited conditions was carried out in pots at PMAS Arid Agriculture University, Rawalpindi, Pakistan. Seeds of two cultivars, i.e., NARC-2009 and Chakwal-50, were taken from the National Agricultural Research Center (NARC). In this experiment, as the source of silicon, silicic acid, sodium silicate, and silica gel were used in the silicon-applied treatments. The effect of silicic acid, sodium silicate, and silica gel at rate of 0.5%, 1.0%, and 1.5% solution was investigated for germination, physiological, and yield traits, and it was compared with control. Physiological parameters like leaf membrane stability index, epicuticular wax, crop growth rate, relative water content, stomatal conductance, transpiration rate, photosynthetic rate, leaf area, leaf area index, chlorophyll contents, leaf succulence, relative leaf water contents, silicon concentration in leaves, and proline contents were measured. The results depicted that different silicon rates and application levels have a significant impact upon crop growth and development. Wheat crop responded well to silicon priming treatments. Maximum grain yield was obtained for silica gel with 1.5% silicon application level, whereas minimum grain yield was obtained by control treatment. Similarly, genotypes responded significantly to silicon priming treatments for grain production. Cultivar NARC-2009 performed well under different silicon regime of the rainfed zone of pothwar, while cultivar Chakwal-50 gave less seed production. Silicon priming could be a good viable option in the future to cope abiotic stress.

Improving prediction of chickpea wilt severity using machine learning coupled with model combination techniques under field conditions

Drought is one of the critical environmental stresses that affect growth and development of plants. Plants are damaged directly and indirectly under drought stress. Increasing water stress tolerance in plants is crucial. The aim of this study was to investigate the effects of different water stress levels (-1, -5, and -10 bars) and paclobutrazol application (0 and 50 mg-1) on strawberry cv. Paros. According to analyses of variance there were significant effects of drought stress and paclobutrazol application on leaf area, leaf dry weight, leaf relative water content (RWC), cell membrane stability index (MSI), proline and protein content of leaves. Leaf area, leaf dry weight, leaf relative water content and cell membrane stability index decreased in drought stress, especially at -10 bars. Proline and protein contents were enhanced by increasing water stress levels. Paclobutrazol application increased leaf relative water content and cell membrane stability index, proline and protein contents of leaves. Leaf relative water content was 68.77% in -10 bars drought stress that increased to 79% in paclobutrazol treatment. Also, cell membrane stability index was 69.65% in severe drought stress and reached to 77% in paclobutrazol treatment. According to the results pacloburazol is a benefit substance to ameliorate drought stress effects in strawberry cv. Paros.