Earlier Estimates Research Articles

Ensemble Learning for Pea Yield Estimation Using Unmanned Aerial Vehicles, Red Green Blue, and Multispectral Imagery

Peas are one of the most important cultivated legumes worldwide, for which early yield estimations are helpful for agricultural planning. The unmanned aerial vehicles (UAVs) have become widely used for crop yield estimations, owing to their operational convenience. In this study, three types of sensor data (red green blue [RGB], multispectral [MS], and a fusion of RGB and MS) across five growth stages were applied to estimate pea yield using ensemble learning (EL) and four base learners (Cubist, elastic net [EN], K nearest neighbor [KNN], and random forest [RF]). The results showed the following: (1) the use of fusion data effectively improved the estimation accuracy in all five growth stages compared to the estimations obtained using a single sensor; (2) the mid filling growth stage provided the highest estimation accuracy, with coefficients of determination (R2) reaching up to 0.81, 0.8, 0.58, and 0.77 for the Cubist, EN, KNN, and RF algorithms, respectively; (3) the EL algorithm achieved the best performance in estimating pea yield than base learners; and (4) the different models were satisfactory and applicable for both investigated pea types. These results indicated that the combination of dual-sensor data (RGB + MS) from UAVs and appropriate algorithms can be used to obtain sufficiently accurate pea yield estimations, which could provide valuable insights for agricultural remote sensing research.

Escalation to conflict as an ongoing process: the case of July 1914

ABSTRACT The sequence leading to conflict, as specifically in July 1914, reveals the changes in each protagonist’s propensity to wage war. To characterize its timing, escalation is viewed as a viability (differential) game in progress under the protagonists’ actions. The chronicle of confrontations and accommodations allows for estimating a responsiveness structure at the heart of the game. As the moves, which are the controls, are observed, and not the state variables, the game reduces to the minimization of a viability criterion under dynamics. Early estimation of the responsiveness structure operationalizes the procedure for crisis management and provides a way to anticipate the consequences of possible moves in escalations to conflict. The application to July 1914 shows the strength of the method.

Plot-level satellite imagery can substitute for UAVs in assessing maize phenotypes across multistate field trials.

Abstract Accurate genotype-specific early yield estimates at fields and plots offer potential benefits to farmers in optimizing their agronomic practices, breeders in screening thousands of varieties, and policymakers in decision-making contributing to the improvement of agriculture and food production systems. Effective approaches to track plant growth and predict yield require large datasets of remote sensing and ground truth data collected across multiple environments. Low-altitude drone flights are increasingly being used to collect data from field evaluations of new crop varieties, while satellite imagery is being explored to track yield and management practices at the regional scales. Despite their lower spatial resolution, satellite platforms exhibit logistical and technical advantages in scalability and accessibility, and could facilitate plot-level predictions, especially with steadily improving spatial resolution. However, genotype-specific, plot-level, high-resolution satellite images from multiple environments with ground truth measurements are not yet publicly available. Here we generated, described, and evaluated over 20,000 plot-level images of over 80 hybrid maize varieties grown across the US corn belt under various management practices collected from (near simultaneous) satellite and drone flights integrated with ground truth yield measurement. Of the six baseline models examined, models employing data collected from satellite images often matched or exceeded the performance of models employing drone images for both within and cross-environment yield prediction. Large, multi-environment, genetically diverse datasets such as those generated in this study, along with more complex models could help unlock the power of satellite imagery as an important addition to the tool of farmers, plant geneticists, breeders, and policymakers.

Research on the Energy Consumption Influence Mechanism and Prediction for the Early Design Stage of University Public Teaching Buildings in Beijing

The public teaching buildings of universities have a large flow of people, high lighting requirements, and large energy consumption, which present significant potential for energy saving. The greatest opportunity for integrating “green” architectural design strategies lies in the design phase, especially the early stage of architectural design. However, current designers often rely on experience or qualitative judgment for decision-making. Thus, there is a pressing need for rational and quantitative green architectural design theories and techniques to guide and support decision-making for the design parameters of teaching buildings. This study, based on field surveys of 40 teaching buildings, constructs building archetypes regarding energy consumption including 28 typical values. Based on the “Rectangle”, “L”, “U”, and “Courtyard” archetypes, through batch energy consumption simulation and multiple regression methods, the influence mechanisms of nine energy consumption influencing factors on four types of building energy consumptions were explored, and energy consumption prediction models were derived. The findings of this research can serve as factor evaluation and selection in the early stage of architectural design for public teaching buildings at universities, and the prediction model can assist in the early estimation of energy consumption. This aims to enrich and supplement green architectural design methods by supporting the design of green public teaching buildings and providing reference and application for relevant engineering practices.

Abstract PO3-10-06: Parenting While Living with Cancer - Providing Better Outcomes for Families During the Cancer Journey

Abstract For over 20 years, Kesem has been dedicated to supporting children impacted by a parent’s cancer. To better understand the stresses on a family navigating cancer, Kesem completed a several month research program rooted in Diversity, Equity, and Inclusion (DEI) and consisting of ethnographic research, quantitative surveys, focus groups, benchmarking, and data analytics. We are using this research to develop a deeper understanding of the personal stories of families impacted by a cancer diagnosis and of the current data from experts in the field. Kesem is sharing our research findings in order for the general oncology space to better serve parents living with cancer. The research included three weeks of ethnographic research completed in rural Mississippi, the Pacific Northwest, and southern Nevada. The research team completed 124 interviews in 18 cities, gathering deep insights about being a parent while living with cancer. The team also reviewed over 30 databases and conducted a survey of approximately 150 parents with cancer. Little has been published about parental cancer in the past decade. Using literature reviews and data such as the 2020 decennial census, we have been able to generate a more accurate assessment of need than ever, confirming earlier estimates that there are approximately five million children in the United States who have a parent with cancer. This means that the average percentage of children under 18 who have experience with parental cancer is between 3.6%–5.5%. The following key takeaways from this research are helpful for all who support patients, including oncologists, nurse navigators, and patient advocates: Based on this research and our ongoing internal survey results, we know that patients generally have less anxiety when they know their children will receive a lifetime of support. Children who are supported are more likely to create a community of support for themselves, do better academically, and have increased mental health. This leads to better outcomes for the entire family. Citation Format: Alicia Kabir. Parenting While Living with Cancer - Providing Better Outcomes for Families During the Cancer Journey [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO3-10-06.

Import shocks and voting behavior in Europe revisited

We provide first evidence for the long-run causal impact that Chinese imports to European regions had on voting outcomes and revisit earlier estimates of the short-run impact for a methodological reason. The fringes of the political spectrum gained ground many years after the China shock plateaued and, unlike an earlier study by Colantone and Stanig (2018b), we do not find any robust evidence for a short-run effect on far-right votes. Instead, far-left and populist parties gained in the short run. We identify persistent long-run effects of import shocks on voting. These effects are biased towards populism and, to a lesser extent, to the far-right.

Nowcasting of advance estimates of personal consumption of Services in the U.S. National Economic Accounts: Individual vs forecasting combination approach

AbstractAs part of continuing effort to research statistical methods for producing timely and accurate early estimates of national accounts statistics, this paper evaluates the ability of individual nowcasting and forecast combination techniques to reduce revisions in the first or advance estimates of U.S. quarterly personal consumption of services at the most detailed component level. At such a level, designated indicators for advance estimates are those directly relevant to the detailed components. Using the same indicators that were used in routine compilations, we show in a real time setting that nowcasting methods are able to reduce revisions in the advance estimates in over 90 percent of the detailed components, and the upper bound of the reductions reached over 60 percent. We evaluate the performances of all methods by comparing their root mean squared revisions for each component. Our study suggests that nowcasting techniques are potentially a powerful tool to reduce revisions in the early estimates in the national account statistics at the most detailed level.

Uncertainty quantification in hydrogen tank exchange: Estimating maintenance costs for new aircraft concepts

The increasing demand for sustainable air mobility has led to the development of innovative aircraft designs, necessitating a balance between environmental responsibility and profitability. However, despite technological advancements, there is still limited understanding of the maintenance implications for hydrogen systems in aviation. The aim of this study is to estimate the maintenance costs of replacing the hydrogen storage system in an aircraft as part of its life cycle costs. To achieve this, we compared conventional and hydrogen-powered aircraft. As there is insufficient data for new aircraft concepts, typical probabilistic methods are not applicable. However, by combining global sensitivity analysis with Dempster–Shafer Theory of Evidence and discrete event simulation, it is possible to identify key uncertainties that impact maintenance costs and economic efficiency. This innovative framework offers an early estimate of maintenance costs under uncertainty, enhancing understanding and assisting in decision-making when integrating hydrogen storage systems and new aviation technologies.

Mango Tree Dataset for Yield Estimation: Some Exploratory Analysis

Objectives: Employing computer vision methods for yield estimation requires standard datasets. However, unavailability of such a dataset in the literature limits the researchers from evaluating and comparing the performance of their proposed algorithms. In this paper, a benchmark of mango tree dataset is introduced. Methods: The dataset is gathered over a 5-month period, starting from the fruit's blossoming stage and ending with its ripening stage. There are 21,000 photos of 4 distinct mango tree varieties in the dataset. From each cultivar, images are captured with different views, distances, and daylight conditions. Further, preprocessing, and exploratory analysis of the dataset are carried out by extracting a few global features such as colors, textures, and histograms for intra-class and inter-class mango trees. Findings: The analysis of the collected dataset with different color layers by extracting a few global features and classification of the cultivars of mango trees and, based on the results obtained, the optimal layer of color is attained for the further yield estimation process. Novelty: Exploratory analysis of a novel temporal mango crop dataset is executed, and a color analysis classification method is proposed to aid in the early estimation of mango fruit crop yields. Keywords: Mango Fruit, Yield Estimation, Temporal Dataset, Feature Extraction, Tree Classification

Personalized prognosis stratification of newly diagnosed glioblastoma applying a statistical decision tree model

PurposeGlioblastoma (GBM) is the most frequent glioma in adults with a high treatment resistance resulting into limited survival. The individual prognosis varies depending on individual prognostic factors, that must be considered while counseling patients with newly diagnosed GBM. The aim of this study was to elaborate a risk stratification algorithm based on reliable prognostic factors to facilitate a personalized prognosis estimation early on after diagnosis.MethodsA consecutive patient cohort with confirmed GBM treated between 2010 and 2021 was retrospectively analyzed. Clinical, radiological, and molecular parameters were assessed and included in the analysis. Overall survival (OS) was the primary outcome parameter. After identifying the strongest prognostic factors, a risk stratification algorithm was elaborated with estimated odds of survival.ResultsA total of 462 GBM patients were analyzed. The strongest prognostic factors were Charlson Comorbidity Index (CCI), extent of tumor resection, and adjuvant treatment. Patients with CCI ≤ 1 receiving tumor resection had the highest survival odds (88% for 10 months). On the contrary, patients with CCI > 3 receiving no adjuvant treatment had the lowest survival odds (0% for 10 months). The 10-months survival rate in patients with CCI > 3 receiving adjuvant treatment was 56% for patients younger than 70 years and 22% for patients older than 70 years.ConclusionA risk stratification algorithm based on significant prognostic factors allowed a personalized early prognosis estimation at the time of GBM diagnosis, that can contribute to a more personalized patient counseling.

Enhancing Crop Yield Predictions with PEnsemble 4: IoT and ML-Driven for Precision Agriculture

This research introduces the PEnsemble 4 model, a weighted ensemble prediction model that integrates multiple individual machine learning models to achieve accurate maize yield forecasting. The model incorporates unmanned aerial vehicle (UAV) imagery and Internet of Things (IoT)-based environmental data, providing a comprehensive and data-driven approach to yield prediction in maize cultivation. Considering the projected growth in global maize demand and the vulnerability of maize crops to weather conditions, improved prediction capabilities are of paramount importance. The PEnsemble 4 model addresses this need by leveraging comprehensive datasets encompassing soil attributes, nutrient composition, weather conditions, and UAV-captured vegetation imagery. By employing a combination of Huber and M estimates, the model effectively analyzes temporal patterns in vegetation indices, in particular CIre and NDRE, which serve as reliable indicators of canopy density and plant height. Notably, the PEnsemble 4 model demonstrates a remarkable accuracy rate of 91%. It advances the timeline for yield prediction from the conventional reproductive stage (R6) to the blister stage (R2), enabling earlier estimation and enhancing decision-making processes in farming operations. Moreover, the model extends its benefits beyond yield prediction, facilitating the detection of water and crop stress, as well as disease monitoring in broader agricultural contexts. By synergistically integrating IoT and machine learning technologies, the PEnsemble 4 model presents a novel and promising solution for maize yield prediction. Its application holds the potential to revolutionize crop management and protection, contributing to efficient and sustainable farming practices.

Performance of UAV-derived Normalized Difference Vegetation Index (NDVI) for Early Estimation of Rice Yield

Traditionally, the rice yield is measured after the harvest, which is too late then to revert any agronomic practices to improve yield. The aerial spectral reflectance images of crops captured by a multispectral camera mounted in an Unmanned Aerial Vehicle (UAV) are capable of quantitatively measuring the internal physiological condition of crops directly associated with their health status. The aim of this study was to evaluate the performance of UAV-multispectral image derived-NDVI as a method for estimating rice yield. Multispectral drone images including single band images were acquired from a controlled rice field at Rice Research and Development Institute (RRDI), Sri Lanka. Rice variety Bg 300 was cultivated in the Yala season under four levels of Nitrogen (N) fertilizer treatment plots. According to the regression co-relation analysis the derived NDVI values at 15 and 25 m flying heights from the rice crops at the booting stage were moderately (R2=0.65 and R2=0.67, p<0.05, respectively) associated with the actual yield. The derived NDVI values indicated the rice crop vigor at the booting stage is a useful indicator for early estimation of the rice yield prior to actual harvest.

Clinical aspects and treatment of tricuspid valve regurgitation

Tricuspid regurgitation (TR) leading to right heart failure is prevalent and associated with increased mortality. The significant under-recognition of the disease resulted from insufficient medical therapies and the high associated risk of surgical therapy. Over the last decade there has been a rapid development of interventional treatment options so that the disease has increasingly become the focus of attention of specialists in internal medicine and interventional cardiologists. The etiology of TR is differentiated into primary TR, secondary atrial TR, secondary ventricular TR and TR associated with cardiac implantable electronic devices (CIED). The TR was identified as an independent predictor of mortality, independent of associated diseases such as atrial fibrillation, left-sided heart failure or pulmonary hypertension. Even patients with low to moderate TR have asignificantly increased risk of mortality. Early diagnostics and estimation of the severity by echocardiography as well as timely referral to atertiary heart valve center are decisive in order to evaluate possible treatment options before irreversible right ventricular damage and secondary organ dysfunction occur. For transcatheter edge-to-edge repair and transcatheter tricuspid valve replacement there is now first evidence from randomized controlled studies. While the understanding of TR is continuously improving, new tricuspid valve repair and replacement systems are in a state of steady progress. Whether the treatment has an effect on reduction of the mortality and stabilization of right ventricular failure with a reduction in hospitalization, will first be shown in future studies.

A NONLINEAR REGRESSION MODEL FOR EARLY LOC ESTIMATION OF OPEN-SOURCE KOTLIN-BASED APPLICATIONS

Context. The early lines of code (LOC) estimation in software projects holds significant importance, as it directly influences the prediction of development effort, covering a spectrum of different programming languages, and open-source Kotlin-based applications in particular. The object of the study is the process of early LOC estimation of open-source Kotlin-based apps. The subject of the study is the nonlinear regression models for early LOC estimation of open-source Kotlin-based apps. Objective. The goal of the work is to build the nonlinear regression model with three predictors for early LOC estimation of open-source Kotlin-based apps based on the Box-Cox four-variate normalizing transformation to increase the confidence in early LOC estimation of these apps. Method. For early LOC estimation in open-source Kotlin-based apps, the model, confidence, and prediction intervals of nonlinear regression were constructed using the Box-Cox four-variate normalizing transformation and specialized techniques. These techniques, relying on multiple nonlinear regression analyses incorporating multivariate normalizing transformations, account for the dependencies between variables in non-Gaussian data scenarios. As a result, this method tends to reduce the mean magnitude of relative error (MMRE) and narrow confidence and prediction intervals compared to models utilizing univariate normalizing transformations. Results. An analysis has been carried out to compare the constructed model with nonlinear regression models employing decimal logarithm and Box-Cox univariate transformation. Conclusions. The nonlinear regression model with three predictors for early LOC estimation of open-source Kotlin-based apps is constructed using the Box-Cox four-variate transformation. Compared to the other nonlinear regression models, this model demonstrates a larger multiple coefficient of determination, a smaller value of the MMRE, and narrower confidence and prediction intervals. The prospects for further research may include the application of other data sets to construct the nonlinear regression model for early LOC estimation of open-source Kotlin-based apps for other restrictions on predictors.

Subcontracting Retreat: Early Estimates Using Administrative Data

Labor flexibility policies have increased temporary and subcontracted jobs. These types of employment are associated with lower quality jobs. In this paper, five-year economic census data and social security administrative data were collected to estimate, in non-census years, out-of-sample the percentage of subcontracted jobs. This evidence is relevant for assessing the impact of a legislation that banned subcontracting. Predictor variables such as time fixed effects, industry, and the rate of temporary workers were used. The results show a significant decrease in subcontracting, particularly in the secondary sector. These findings raise the need for future research on improvements in post-reform well-being in the labor market.

EPOCHS. II. The Ultraviolet Luminosity Function from 7.5 < z < 13.5 Using 180 arcmin2 of Deep, Blank Fields from the PEARLS Survey and Public JWST Data

We present an analysis of the ultraviolet luminosity function (UV LF) and star formation rate density of distant galaxies (7.5 < z < 13.5) in the “blank” fields of the Prime Extragalactic Areas for Reionization and Lensing Science (PEARLS) survey combined with Early Release Science data from the CEERS, GLASS, and NGDEEP surveys/fields and the first data release of JADES. We use strict quality cuts on EAZY photometric redshifts to obtain a reliable selection and characterization of high-redshift (z > 6.5) galaxies from a consistently processed set of deep, near-infrared imaging. Within an area of 180 arcmin2, we identify 1046 candidate galaxies at redshifts z > 6.5 and we use this sample to study the UV LF in four redshift bins between 7.5 < z < 13.5. The measured number density of galaxies at z = 8 and z = 9 matches those of past observations undertaken by the Hubble Space Telescope (HST). Our z = 10.5 measurements lie between early James Webb Space Telescope (JWST) results and past HST results, indicating cosmic variance may be the cause of previous high density measurements. However, the number densities of UV-luminous galaxies at z = 12.5 are high compared to predictions from simulations. When examining the star formation rate density of galaxies at this period, our observations are still largely consistent with a constant star formation efficiency, are slightly lower than previous early estimations using JWST, and support galaxy driven reionization at z ≤ 8.

Shear Alfvén waves within magnetic islands

We calculate Alfvén eigenmodes within a magnetic island (MiAE) which have been conjectured over a decade ago. Starting from a cylindrical plasma equilibrium, we calculate the complete metric of the island interior assuming an iota profile with a constant shear for Wendelstein 7-X parameters. Then, we solve the resulting Magneto-Hydrodynamic equations inside the island optionally considering Finite Larmor Radius corrections. We find various eigenmodes in the lowest gaps for n = 0. The eigenmode with the lowest frequency shows a weakly non-linear dependence on the island width which deviates considerably from an earlier estimate.

Magnetic Fields in the Southern Coalsack and Beyond

Starlight polarimetry, when combined with accurate distance measurements, allows for exploration of the three-dimensional structure of local magnetic fields in great detail. We present optical polarimetric observations of stars in and close to the Southern Coalsack, taken from the Interstellar Polarization Survey. Located in five fields of view approximately 0.°3 × 0.°3 in size, these data represent the highest density of optical polarimetric observations in the Southern Coalsack to date. Using these data, combined with accurate distances and extinctions based on Gaia data, we are able to characterize the magnetic field of the Coalsack and disentangle contributions to the polarization caused by the Southern Coalsack and a background structure. For the Southern Coalsack, we find an average magnetic field orientation of θ ∼ 75° with respect to the Galactic north pole and an average plane-of-sky magnetic field strength of approximately B POS = 10 μG, using the Davis–Chandrasekhar–Fermi method. These values are in agreement with some earlier estimates of the Coalsack’s magnetic field. In order to study the distant structure, we introduce a simple method to separate and isolate the polarization of distant stars from foreground contribution. For the distant structure, which we estimate to be located at a distance of approximately 1.3–1.5 kpc, we find an average magnetic field orientation of θ ∼ 100° and estimate a field strength of B POS ∼ 10 μG, although this will remain highly uncertain until the precise nature of the distant structure can be uncovered.

A Cloud-Based Deep Learning Framework for Downy Mildew Detection in Viticulture Using Real-Time Image Acquisition from Embedded Devices and Drones

In viticulture, downy mildew is one of the most common diseases that, if not adequately treated, can diminish production yield. However, the uncontrolled use of pesticides to alleviate its occurrence can pose significant risks for farmers, consumers, and the environment. This paper presents a new framework for the early detection and estimation of the mildew’s appearance in viticulture fields. The framework utilizes a protocol for the real-time acquisition of drones’ high-resolution RGB images and a cloud-docker-based video or image inference process using object detection CNN models. The authors implemented their framework proposition using open-source tools and experimented with their proposed implementation on the debina grape variety in Zitsa, Greece, during downy mildew outbursts. The authors present evaluation results of deep learning Faster R-CNN object detection models trained on their downy mildew annotated dataset, using the different object classifiers of VGG16, ViTDet, MobileNetV3, EfficientNet, SqueezeNet, and ResNet. The authors compare Faster R-CNN and YOLO object detectors in terms of accuracy and speed. From their experimentation, the embedded device model ViTDet showed the worst accuracy results compared to the fast inferences of YOLOv8, while MobileNetV3 significantly outperformed YOLOv8 in terms of both accuracy and speed. Regarding cloud inferences, large ResNet models performed well in terms of accuracy, while YOLOv5 faster inferences presented significant object classification losses.

Computational prediction of workability and mechanical properties of bentonite plastic concrete using multi-expression programming

Bentonite plastic concrete (BPC) demonstrated promising potential for remedial cut-off wall construction to mitigate dam seepage, as it fulfills essential criteria for strength, stiffness, and permeability. High workability and consistency are essential attributes for BPC because it is poured into trenches using a tremie pipe, emphasizing the importance of accurately predicting the slump of BPC. In addition, prediction models offer valuable tools to estimate various strength parameters, enabling adjustments to BPC mixing designs to optimize project construction, leading to cost and time savings. Therefore, this study explores the multi-expression programming (MEP) technique to predict the key characteristics of BPC, such as slump, compressive strength (fc), and elastic modulus (Ec). In the present study, 158, 169, and 111 data points were collected from the experimental studies for the slump, fc, and Ec, respectively. The dataset was divided into three sets: 70% for training, 15% for testing, and another 15% for model validation. The MEP models exhibited excellent accuracy with a correlation coefficient (R) of 0.9999 for slump, 0.9831 for fc, and 0.9300 for Ec. Furthermore, the comparative analysis between MEP models and conventional linear and non-linear regression models revealed remarkable precision in the predictions of the proposed MEP models, surpassing the accuracy of traditional regression methods. SHapley Additive exPlanation analysis indicated that water, cement, and bentonite exert significant influence on slump, with water having the greatest impact on compressive strength, while curing time and cement exhibit a higher influence on elastic modulus. In summary, the application of machine learning algorithms offers the capability to deliver prompt and precise early estimates of BPC properties, thus optimizing the efficiency of construction and design processes.