Showing papers by "James Taylor published in 2022"

A review of methods to evaluate crop model performance at multiple and changing spatial scales

Abstract: Abstract Crop models are useful tools because they can help understand many complex processes by simulating them. They are mainly designed at a specific spatial scale, the field. But with the new spatial data being made available in modern agriculture, they are being more and more applied at multiple and changing scales. These applications range from typically at broader scales, to perform regional or national studies, or at finer scales to develop modern site-specific management approaches. These new approaches to the application of crop models raise new questions concerning the evaluation of their performance, particularly for downscaled applications. This article first reviews the reasons why practitioners decide to spatialize crop models and the main methods they have used to do this, which questions the best place of the spatialization process in the modelling framework. A strong focus is then given to the evaluation of these spatialized crop models. Evaluation metrics, including the consideration of dedicated sensitivity indices are reviewed from the published studies. Using a simple example of a spatialized crop model being used to define management zones in precision viticulture, it is shown that classical model evaluation involving aspatial indices (e.g. the RMSE) is not sufficient to characterize the model performance in this context. A focus is made at the end of the review on potentialities that a complementary evaluation could bring in a precision agriculture context.

Yield sensing technologies for perennial and annual horticultural crops: a review

Abstract: Abstract Yield maps provide a detailed account of crop production and potential revenue of a farm. This level of details enables a range of possibilities from improving input management, conducting on-farm experimentation, or generating profitability map, thus creating value for farmers. While this technology is widely available for field crops such as maize, soybean and grain, few yield sensing systems exist for horticultural crops such as berries, field vegetable or orchards. Nevertheless, a wide range of techniques and technologies have been investigated as potential means of sensing crop yield for horticultural crops. This paper reviews yield monitoring approaches that can be divided into proximal, either direct or indirect, and remote measurement principles. It reviews remote sensing as a way to estimate and forecast yield prior to harvest. For each approach, basic principles are explained as well as examples of application in horticultural crops and success rate. The different approaches provide whether a deterministic (direct measurement of weight for instance) or an empirical (capacitance measurements correlated to weight for instance) result, which may impact transferability. The discussion also covers the level of precision required for different tasks and the trend and future perspectives. This review demonstrated the need for more commercial solutions to map yield of horticultural crops. It also showed that several approaches have demonstrated high success rate and that combining technologies may be the best way to provide enough accuracy and robustness for future commercial systems.

Potential of Multiway PLS (N-PLS) Regression Method to Analyse Time-Series of Multispectral Images: A Case Study in Agriculture

Abstract: Recent literature reflects the substantial progress in combining spatial, temporal and spectral capacities for remote sensing applications. As a result, new issues are arising, such as the need for methodologies that can process simultaneously the different dimensions of satellite information. This paper presents PLS regression extended to three-way data in order to integrate multiwavelengths as variables measured at several dates (time-series) and locations with Sentinel-2 at a regional scale. Considering that the multi-collinearity problem is present in remote sensing time-series to estimate one response variable and that the dataset is multidimensional, a multiway partial least squares (N-PLS) regression approach may be relevant to relate image information to ground variables of interest. N-PLS is an extension of the ordinary PLS regression algorithm where the bilinear model of predictors is replaced by a multilinear model. This paper presents a case study within the context of agriculture, conducted on a time-series of Sentinel-2 images covering regional scale scenes of southern France impacted by the heat wave episode that occurred on 28 June 2019. The model has been developed based on available heat wave impact data for 107 vineyard blocks in the Languedoc-Roussillon region and multispectral time-series predictor data for the period May to August 2019. The results validated the effectiveness of the proposed N-PLS method in estimating yield loss from spectral and temporal attributes. The performance of the model was evaluated by the R2 obtained on the prediction set (0.661), and the root mean square of error (RMSE), which was 10.7%. Limitations of the approach when dealing with time-series of large-scale images which represent a source of challenges are discussed; however, the N–PLS regression seems to be a suitable choice for analysing complex multispectral imagery data with different spectral domains and with a clear temporal evolution, such as an extreme weather event.

Interval forecasts of weekly incident and cumulative COVID-19 mortality in the United States: A comparison of combining methods

Abstract: Background A combined forecast from multiple models is typically more accurate than an individual forecast, but there are few examples of studies of combining in infectious disease forecasting. We investigated the accuracy of different ways of combining interval forecasts of weekly incident and cumulative coronavirus disease-2019 (COVID-19) mortality. Methods We considered weekly interval forecasts, for 1- to 4-week prediction horizons, with out-of-sample periods of approximately 18 months ending on 8 January 2022, for multiple locations in the United States, using data from the COVID-19 Forecast Hub. Our comparison involved simple and more complex combining methods, including methods that involve trimming outliers or performance-based weights. Prediction accuracy was evaluated using interval scores, weighted interval scores, skill scores, ranks, and reliability diagrams. Results The weighted inverse score and median combining methods performed best for forecasts of incident deaths. Overall, the leading inverse score method was 12% better than the mean benchmark method in forecasting the 95% interval and, considering all interval forecasts, the median was 7% better than the mean. Overall, the median was the most accurate method for forecasts of cumulative deaths. Compared to the mean, the median’s accuracy was 65% better in forecasting the 95% interval, and 43% better considering all interval forecasts. For all combining methods except the median, combining forecasts from only compartmental models produced better forecasts than combining forecasts from all models. Conclusions Combining forecasts can improve the contribution of probabilistic forecasting to health policy decision making during epidemics. The relative performance of combining methods depends on the extent of outliers and the type of models in the combination. The median combination has the advantage of being robust to outlying forecasts. Our results support the Hub’s use of the median and we recommend further investigation into the use of weighted methods.

A universal model for the evolution of tidally stripped systems

Abstract: Accurate models of the structural evolution of dark matter subhaloes, as they orbit within larger systems, are fundamental to understanding the detailed distribution of dark matter at the present day. Numerical simulations of subhalo evolution support the idea that the mass loss associated with tidal stripping is most naturally understood in energy space, with the particles that are the least bound being removed first. Starting from this premise, we recently proposed a zero-parameter ‘energy-truncation model’ for subhalo evolution. We tested this model with simulations of tidal stripping of satellites with initial NFW profiles, and showed that the energy-truncation model accurately predicts both the mass loss and density profiles. In this work, we apply the model to a variety of Hernquist, Einasto and King profiles. We show that it matches the simulation results quite closely in all cases, indicating that it may serve as a universal model to describe tidally stripped collisionless systems. A key prediction of the energy-truncation model is that the central density of dark matter subhaloes is conserved as they lose mass; this has important implications for dark matter annihilation calculations, and for other observational tests of dark matter.

Application of Parallel Factor Analysis (PARAFAC) to the Regional Characterisation of Vineyard Blocks Using Remote Sensing Time Series

Abstract: Monitoring wine-growing regions and maximising the value of production based on their region/local specificities requires accurate spatial and temporal monitoring. The increasing amount and variability of information from remote sensing data is a potential tool to assess this challenge for the grape and wine industry. This article provides a first insight into the capacity of a multiway analysis method applied to Sentinel-2 time series to assess the value of simultaneously considering spectral and temporal information to highlight site-specific canopy evolution in relation to environmental factors and management practices, which present a large diversity at this regional scale. Parallel Factor Analysis (PARAFAC) was used as an unsupervised technique to recover pure spectra and temporal signatures from multi-way spectral imagery of vineyards in the Languedoc-Roussillon region in the south of France. The model was developed using a time series of Sentinel-2 satellite imagery collected over 4978 vineyard blocks between May 2019 and August 2020. From the Sentinel-2 (spectral and temporal) signal, the PARAFAC analysis allowed the identification of spectral and temporal profiles in the form of pure components, which corresponded to vegetation and soil. The PARAFAC analysis also identified that two of the pure spectra were strongly related to characteristics and dynamics of vineyard cultivation at a regional scale. A conceptual framework was proposed in order to simultaneously consider both vegetation and soil profiles and to summarise the mass of data accordingly. This methodology allowed the computation of a concentration index that characterised how close a field was to a vegetation or a soil profile over the season. The concentration indices were validated for the vegetation and the soil over two growing seasons (2019 and 2020) with geostatistical analysis. A non-random distribution of the concentration index at the regional scale was assumed to highlight a strongly spatially organised phenomenon related to spatially organised environmental factors (soil, climate, training system, etc.). In a second step, spatial patterns of indices were subjected to the expertise of a panel of advisors of the wine industry in order to validate them in relation to vine-growing conditions. Results showed that the introduction of the PARAFAC method opened up the possibility to identify relevant spectro-temporal profiles for vine monitoring purposes.

A Comparison of Methods for Forecasting Value-at-Risk and Expected Shortfall of Cryptocurrencies

Abstract: Several procedures to forecast daily risk measures in cryptocurrency markets have been recently implemented in the literature. Among them, long-memory processes, procedures taking into account the presence of extreme observations, procedures that include more than a single regime, and quantile regression-based models have performed substantially better than standard methods in terms of forecasting risk measures. Those procedures are revisited in this paper, and their value at risk and expected shortfall forecasting performance are evaluated using recent Bitcoin and Ethereum data that include periods of turbulence due to the COVID-19 pandemic, the third halving of Bitcoin, and the Lexia class action. Additionally, in order to mitigate the influence of model misspecification and enhance the forecasting performance obtained by individual models, we evaluate the use of several forecast combining strategies. Our results, based on a comprehensive backtesting exercise, reveal that, for Bitcoin, there is no single procedure outperforming all other models, but for Ethereum, there is evidence showing that the GAS model is a suitable alternative for forecasting both risk measures. We found that the combining methods were not able to outperform the better of the individual models. © 2022 John Wiley & Sons Ltd.

Probabilistic load forecasting using post-processed weather ensemble predictions

Abstract: Abstract Probabilistic forecasting of electricity demand (load) facilitates the efficient management and operations of energy systems. Weather is a key determinant of load. However, modelling load using weather is challenging because the relationship cannot be assumed to be linear. Although numerous studies have focussed on load forecasting, the literature on using the uncertainty in weather while estimating the load probability distribution is scarce. In this study, we model load for Great Britain using weather ensemble predictions, for lead times from one to six days ahead. A weather ensemble comprises a range of plausible future scenarios for a weather variable. It has been shown that the ensembles from weather models tend to be biased and underdispersed, which requires that the ensembles are post-processed. Surprisingly, the post-processing of weather ensembles has not yet been employed for probabilistic load forecasting. We post-process ensembles based on: (1) ensemble model output statistics: to correct for bias and dispersion errors by calibrating the ensembles, and (2) ensemble copula coupling: to ensure that ensembles remain physically consistent scenarios after calibration. The proposed approach compares favourably to the case when no weather information, raw weather ensembles or post-processed ensembles without ensemble copula coupling are used during the load modelling.

Local influence of climate on grapevine: an analytical process involving a functional and Bayesian exploration of farm data time series synchronised with an eGDD thermal index

Abstract: Climate influence on grapevine physiology is prevalent and this influence is expected to increase with climate change. Climate influence on grapevine physiology can vary depending on the terroir. A better understanding of these local terroir variations is likely to be achieved with analyses that use local data; i.e., farm/vineyard data. Thus, the challenge lies in exploiting farm data to enable grape growers to understand their own terroir and consequently adapt their practices to the local conditions. In such a context, this article proposes an analytical process to site-specifically study climate influence on grapevine physiology by focusing on time series of the weather data often contained in farm data sets. This article focuses on temperature and precipitation influence on yield in the form of a case study. The analytical process includes the Extended Growing Degree Days (eGDD) and the Bayesian functional Linear regression with Sparse Steps functions (BLiSS) methods in order to detect site-specific periods of strong climate influence on grapevine yield. It uses data from three commercial vineyards situated in the Bordeaux region (France), California (USA) and Israel. In general, the periods of climate influence on grapevine yield detected for the three vineyards identified the same stages of yield development, which have already been studied in the scientific literature. However, some vineyard differences were observed, including: i) different periods of influence associated with a given stage of yield development between the vineyards, ii) different influential weather variables between the three vineyards for a given period, and iii) differing duration of the period of influence associated with a given stage of yield development between the vineyards. These results show the potential of the proposed analytical process for analysing the time series of farm weather data in order to extract site-specific climate indicators of grapevine yield.

Readability of patient educational materials in venous thrombosis. Analysis of the 2021 ESVS guidelines and comparison with other medical societies information.

Abstract: BACKGROUND In order for patients to comprehend health related information, it must be written at a level that can be readily understood by the intended population. During 2021 the European Society for Vascular Surgery (ESVS) published a sub-section about information for patients into its Guidelines on the Management of Venous Thrombosis. METHODS Nine readability measures were used to evaluate the patient educational material regarding venous thrombosis published by seven medical societies: ESVS, Society for Vascular Medicine (SVM), Society for Vascular Surgery (SVS), Vascular Society for Great Britain and Ireland (VS), Australia and New Zealand Society for Vascular Surgery (ANZSVS), Canadian Society for Vascular Surgery (CSVS) and American Heart Association (AHA). RESULTS The mean reading grade level (RGL) for all the 58 recommendations was 10.61 (range 6.4-14.5) and the mean Flesch Reading Ease (FRE) was 56.10 (51.3-62.9), corresponding to a "fairly difficult" reading level. The mean RGL of the ESVS recommendations (11.45, 95% CI, 9.90-13.00) was significantly higher than the others. Post-hoc analysis determined a significant difference between the ESVS and the SVS (10.86, 95% CI, 9.84-11.91) recommendations (p=0.005). All the patient's education information published by the medical societies presented a RGL higher than recommended. The fifteen sub-sections of the information for patients included into the ESVS clinical guidelines presented a mean RGL above 9.5 points, revealing that no one (0%) was written at or below the recommended GRL. The mean FRE was 47.63 (28.2-61.6), corresponding to a "difficult" reading level. CONCLUSIONS Venous thrombosis patient educational materials produced by leading medical societies have readability scores that are above the recommended levels. The innovative patient's information included into the ESVS venous thrombosis guidelines represents an important advance in the amelioration of the medical information for patients but their readability should be improved to adapt the understanding to the general-population.

Optical parametric amplification seeded by four-wave mixing in photonic crystal fibers

Abstract: We report a mid-infrared (MIR) source emitting at 3 μm, employing a novel χ(3)/χ(2) cascaded nonlinear conversion architecture. Picosecond pulses from a 1.064 μm mode-locked Yb:fiber pump laser are used to generate 1.65 μm signal pulses through χ(3) based four-wave mixing in photonic crystal fiber (PCF). The output of the PCF is then directly focused into a periodically poled lithium niobate crystal to generate idler radiation around 3 μm through χ(2) based three-wave mixing between the pump and signal pulses.

AI system for fetal ultrasound in low-resource settings

Abstract: Despite considerable progress in maternal healthcare, maternal and perinatal deaths remain high in low-to-middle income countries. Fetal ultrasound is an important component of antenatal care, but shortage of adequately trained healthcare workers has limited its adoption. We developed and validated an artificial intelligence (AI) system that uses novice-acquired “blind sweep” ultrasound videos to estimate gestational age (GA) and fetal malpresentation. We further addressed obstacles that may be encountered in low-resourced settings. Using a simplified sweep protocol with real-time AI feedback on sweep quality, we have demonstrated the generalization of model performance to minimally trained novice ultrasound operators using low cost ultrasound devices with on-device AI integration. The GA model was non-inferior to standard fetal biometry estimates with as few as two sweeps, and the fetal malpresentation model had high AUC-ROCs across operators and devices. Our AI models have the potential to assist in upleveling the capabilities of lightly trained ultrasound operators in low resource settings. Introduction Despite considerable progress in maternal healthcare in recent decades, maternal and perinatal deaths remain high with 295,000 maternal deaths during and following pregnancy and 2.4 million neonatal deaths each year. The majority of these deaths occur in low-to-middle-income countries (LMICs).1–3 The lack of antenatal care and limited access to facilities that can provide lifesaving treatment for the mother, fetus and newborn contribute to inequities in quality of care and outcomes in these regions.4,5 Obstetric ultrasound is an important component of quality antenatal care. The WHO recommends one routine early ultrasound scan for all pregnant women, but up to 50% of women in developing countries receive no ultrasound screening during pregnancy.6 Fetal ultrasounds can be used to estimate gestational age (GA), which is critical in scheduling and planning for screening tests throughout pregnancy and interventions for pregnancy complications such as preeclampsia and preterm labor. Fetal ultrasounds later in pregnancy can also be used to diagnose fetal malpresentation, which affects up to 3-4% of pregnancies at term and is associated with trauma-related injury during birth, perinatal mortality, and maternal morbidity.7–11 Though ultrasound devices have traditionally been costly, the recent commercial availability of low-cost, battery powered handheld devices could greatly expand access.12,13,14 However, current ultrasound training programs require months of supervised evaluation as well as indefinite continuing education visits for quality assurance.13–18 To address these barriers, prior studies have introduced a protocol where fetal ultrasounds can be acquired by minimally trained operators via a “blind sweep” protocol, consisting of 6 predefined freehand sweeps over the abdomen.19–23 In this study, we used two prospectively collected fetal ultrasound datasets to estimate gestational age and fetal malpresentation while demonstrating key considerations for use by novice users in LMICs: a) validating that it is possible to build blind sweep GA and fetal malpresentation models that run in real-time on mobile devices; b) evaluating generalization of these models to minimally trained ultrasound operators and low cost ultrasound devices; c) describing a modified 2-sweep blind sweep protocol to simplify novice acquisition; d) adding feedback scores to provide real-time information on sweep quality. Blind sweep procedure Blind sweep ultrasounds consisted of a fixed number of predefined freehand ultrasound sweeps over the gravid abdomen. Certified sonographers completed up to 15 sweeps. Novice operators (“novices”), with 8 hours of blind sweep ultrasound acquisition training, completed 6 sweeps. Evaluation of both sonographers and novices was limited to a set of 6 sweeps 3 vertical and 3 horizontal sweeps (Figure 1B). Fetal Age Machine Learning Initiative (FAMLI) and Novice User Study Datasets Data was analyzed from the Fetal Age Machine Learning Initiative cohort, which collected ultrasound data from study sites at Chapel Hill, NC (USA) and the Novice User Study collected from Lusaka, Zambia (Figure 1A).24 The goal of this prospectively collected dataset was to empower development of technology to estimate gestational age.25 Data collection occurred between September 2018 and June 2021. All study participants provided written informed consent, and the research was approved by the UNC institutional review board and the biomedical research ethics committee at the University of Zambia. Studies also included standard clinical assessments of GA and fetal malpresentation performed by a trained sonographer.26 Blind sweep data were collected with standard ultrasound devices (SonoSite M-Turbo or GE Voluson) as well as a low cost portable ultrasound device (ButterflyIQ). Evaluation was performed on the FAMLI (sonographer-acquired) and Novice User Study (novice-acquired) datasets. Test sets consisted of patients independent of those used for AI development (Figure 1A). For our GA model evaluation, the primary FAMLI test set comprised 407 women in 657 study visits in the USA. A second test set, “Novice User Study” included 114 participants in 140 study visits in Zambia. Novice blind sweep studies were exclusively performed at Zambian sites. Sweeps collected with standard ultrasound devices were available for 406 of 407 participants in the sonographer-acquired test set, and 112 of 114 participants in the novice-acquired test set. Sweeps collected with the low cost device were available for 104 of 407 participants in the sonographer-acquired test set, and 56 of 114 participants in the novice-acquired test set. Analyzable data from the low cost device became available later during the study, and this group of patients is representative of the full patient set. We randomly selected one study visit per patient for each analysis group to avoid combining correlated measurements from the same patient. For our fetal malpresentation model, the test set included 613 patients from the sonographer-acquired and novice-acquired datasets, resulting in 65 instances of non-cephalic presentation (10.6%). For each patient, the last study visit of the third trimester was included. Of note, there are more patients in the malpresentation model test set since the ground truth is not dependent on a prior visit. The disposition of study participants are summarized in STARD diagrams (Extended Data Figure 1) and Extended Data Table 1. Mobile-device-optimized AI gestational age and fetal malpresentation estimation We calculated the mean difference in absolute error between the GA model estimate and estimated gestational age as determined by standard fetal biometry measurements using imaging from traditional ultrasound devices operated by sonographers.26 The reference ground truth GA was established as described above (Figure 1A). When conducting pairwise statistical comparisons between blind sweep and standard fetal biometry absolute errors, we established an a priori criterion for non-inferiority which was confirmed if the blind sweep mean absolute error (MAE) was less than 1.0 day greater than the standard fetal biometry’s MAE. Statistical estimates and comparisons were computed after randomly selecting one study visit per patient for each analysis group, to avoid combining correlated measurements from the same patient. We conducted a supplemental analysis of GA model prediction error with mixed effects regression on all test data, combining sonographer-acquired and novice-acquired test sets. Fixed effect terms accounted for the ground truth GA, the type of ultrasound machine used (standard vs. low cost), and the training level of the ultrasound operator (sonographer vs. novice). All patient studies were included in the analysis, and random effects terms accounted for intra-patient and intra-study effects. GA analysis results are summarized in Table 1. The MAE for the GA model estimate with blind sweeps collected by sonographers using standard ultrasound devices was significantly lower than the MAE for the standard fetal biometry estimates (mean difference -1.4 ± 4.5 days, 95% CI -1.8, -0.9 days). There was a trend towards increasing error for bind sweep and standard fetal biometry procedures with gestational week (Figure 2, top left). The accuracy of the fetal malpresentation model for predicting non-cephalic fetal presentation from third trimester blind sweeps was assessed using a reference standard determined by sonographers equipped with traditional ultrasound imagery (described above). We selected the latest study visit in the third trimester for each patient. Data from sweeps performed by the sonographers and novices were analyzed separately. We evaluated the fetal malpresentation model’s area under the receiver operating curve (AUC-ROC) on the test set in addition to non-cephalic sensitivity and specificity. The fetal malpresentation model attained an AUC-ROC of 0.977 (95% CI 0.949, 1.00), sensitivity of 0.938 (95% CI 0.848, 0.983), and specificity of 0.973 (95% CI 0.955, 0.985) (Table 2 and Figure 3). Generalization of GA and malpresentation estimation to novices Our models were trained on up to 15 blind sweeps per study performed by sonographers. No novice-acquired blind sweeps were used to train our models. We assessed GA model generalization to blind sweeps performed by novice operators that performed 6 sweeps. We compared the MAE between novice-performed blind sweep AI estimates and the standard fetal biometry. For the malpresentation model, we reported the AUC-ROC for blind sweeps performed by novices, along with the sensitivity and specificity at the same operating point used for evaluating blind sweeps performed by sonographers. In this novice-acquired dataset, the difference in MAE between blind sweep AI estimates and the standard fetal bio