Yield Model Research Articles

Swin MoCo: Improving parotid gland MRI segmentation using contrastive learning.

Segmentation of the parotid glands and tumors by MR images is essential for treating parotid gland tumors. However, segmentation of the parotid glands is particularly challenging due to their variable shape and low contrast with surroundingstructures. The lack of large and well-annotated datasets limits the development of deep learning in medical images. As an unsupervised learning method, contrastive learning has seen rapid development in recent years. It can better use unlabeled images and is hopeful to improve parotid glandsegmentation. We propose Swin MoCo, a momentum contrastive learning network with Swin Transformer as its backbone. The ImageNet supervised model is used as the initial weights of Swin MoCo, thus improving the training effects on small medical imagedatasets. Swin MoCo trained with transfer learning improves parotid gland segmentation to 89.78% DSC, 85.18% mIoU, 3.60 HD, and 90.08% mAcc. On the Synapse multi-organ computed tomography (CT) dataset, using Swin MoCo as the pre-trained model of Swin-Unet yields 79.66% DSC and 12.73 HD, which outperforms the best result of Swin-Unet on the Synapsedataset. The above improvements require only 4h of training on a single NVIDIA Tesla V100, which is computationally cheap. Swin MoCo provides new approaches to improve the performance of tasks on small datasets. The code is publicly available at https://github.com/Zian-Xu/Swin-MoCo.

Changes in water conservation and possible causes in the Yellow River Basin of China during the recent four decades

As water quality declines and water resources become scarce, water conservation emerges as the central challenge of water resource management and sustainable development in the watershed ecosystem. The Yellow River, known as the “mother river” of China, of which the water conservation function has received significant public attention in the changing environmental conditions. In the study, the InVEST water yield model was utilized to evaluate the spatiotemporal dynamics of water conservation; the MK trend test and Sen’s slope were used to examine the trends of precipitation and water conservation, respectively. Additionally, the response of water conservation to climate, land use, and soil changes during the period 1981–2020 was also discussed. The results showed that under the comprehensive influence of various factors, the water conservation of the YRB showed a decreasing and then increasing trend, which was presumed to be associated with the Grain for Green Project. Water conservation showed an increasing trend in the upstream area of the study area while decreasing in the lower reaches in recent decades. The changes in water conservation function in the YRB resulted from the comprehensive influence of climate factors, soil conditions, and land use types. Besides, woodland and grassland provide the highest water conservation capacity, which initially increased and then decreased with the increase of slope. The spatial analysis emphasized the critical role of water conservation in the Yellow River Basin, particularly highlighting the source area (above Lanzhou Station), the southern tributaries of the Wei River, and the upper reaches of the Yiluo River as significant water conservation zones. These areas should be considered crucial and given priority in regional water resource management and ecological protection efforts. The findings of this study could provide a theoretical foundation for ecological protection and water security in the YRB, which are essential for sustainable development.

From Sunrise to Sunset: Unraveling Metastability in Perovskite Solar Cells by Coupled Outdoor Testing and Energy Yield Modelling

AbstractPerovskite‐based solar cells exhibit peculiar outdoor performance which is not yet fully understood. The results of outdoor tests may contain hidden, but valuable information that cannot be fully extracted from measurements alone. One such phenomenon is the effect of nighttime degradation and the subsequent light‐soaking recovery, which can take from a few hours in the morning up to the entire day. In this work, long‐term outdoor monitoring is combined with energy yield modeling to qualitatively and quantitatively investigate the effect of light‐soaking recovery in both single junction and tandem perovskite‐based devices. Following the novel methodology presented in this study, it is observed that the light‐soaking effect depends not only on the daily irradiation but also on the device temperature, and it can be described using a simple empirical formalism. Incorporating this dependency into the energy yield model results in an excellent agreement between the simulated and the measured outdoor data, which allows to perform long‐term prediction studies. The model estimates that the light‐soaking metastability effect decreases the attainable annual energy yield by up to ≈5% for the studied single junction devices, and for tandems by up to ≈3%, depending on the geographical location, and even more for non‐optimal device orientation.

Palm Oil Yield Prediction using Machine Learning

This project aims to revolutionize palm oil production by leveraging machine learning techniques to develop a predictive model for palm oil yield. By incorporating a wide range of variables such as climate conditions, soil characteristics, and cultivation techniques, the model seeks to provide accurate predictions to stakeholders in the palm oil industry. The ultimate goal is to empower farmers and decision-makers with a tool that can enhance decision-making processes and contribute to the overall sustainability of palm oil production. With the global demand for palm oil on the rise, the need for precision and efficiency in cultivation practices has never been more critical, making this project timely and impactful.

Quantifying Structural Shading and Reflection Effects on Single Axis Tracked Bifacial Photovoltaic System Performance

Structural elements of bifacial photovoltaic (PV) systems, such as module frames, module supports, and torque tubes, affect module rear irradiance profiles through both shading and reflection. Standard bifacial energy yield models represent racking effects as a flat rear irradiance de‐rate factor; however, this neglects 1) the impact of racking reflection, and 2) the variation of racking effects over time. In this work, a differential irradiance approach is presented to quantify the effect of racking shading and reflection on bifacial rear irradiance. Using this method, racking effects on system energy yield, irradiance mismatch losses, and bifacial gain are calculated. This is applied to a single‐axis‐tracked 2‐in‐portrait bifacial PV system in Livermore, California with 74.5% reflective racking using bifacial_radiance ray tracing software. Racking reflection counteracts the irradiance reduction and mismatch losses caused by racking shading. Racking reflection reduces average rear irradiance shading by up to 19.2% per timestamp and 9.1% per year compared to absorptive racking. Racking effects vary diurnally, seasonally, and with respect to albedo. In a single day, the impact of racking on rear irradiance varies up to 14.6%. Applying this method will improve energy yield modeling accuracy of bifacial PV systems.

Strip electro-mechanical yield model for three equal straight collinear cracks in piezoelectric materials

This paper is devoted to the development of a model to study three straight collinear cracks in piezoelectric materials under the influence of combined electrical and mechanical loading conditions. Mathematical relationships for the size of yield zones with mechanical yielding conditions and the saturation zone sizes to applied electrical field has been established. To make this plausible, two different cases are considered: first when the electrical saturation zones are bigger than the mechanical yield zones while other case in which situation is just opposite. Closed-form analytic expressions are derived for various fracture parameters with the help of well known complex variable method. Numerical results are presented to study the multiple cracks in different piezoelectric materials. Results obtained are reported graphically, analyzed and concluded.

A new drought model for disaster risk management in the Punjab, Sindh and Baluchistan provinces of Pakistan

Drought poses a continual threat to both lives and livelihoods in the Global South. Although the impact on food security from drought could be reduced through early release of funds, the humanitarian sector typically reacts to crises rather than anticipates them. A significant challenge lies in devising a drought monitoring and forecasting system that can function across environmentally and economically diverse regions. This is particularly evident in Pakistan, which encompasses environments ranging from fertile riverbeds to arid deserts. This paper details the development, implementation, and operation of an anticipatory drought Disaster Risk Financing (DRF) programme for the provinces of Punjab, Sindh, and Baluchistan in Pakistan. Key to the DRF development are a new yield model for the primary crop in the target season (winter wheat), and a novel forecasting system for four seasonal drought indicators - namely winter wheat yield, precipitation, normalised difference vegetation index (NDVI) and vegetation health index (VHI). Formal evaluations demonstrate that the forecasts are skillful up to 2 months in advance of the end of the season – enabling anticipatory release of funds. The work presented here is applicable beyond Pakistan. Indeed, the model and the methodologies are sufficiently broad and adaptable to be utilised in arid and semi-arid regions across the Global South.

Approximation of reliabilities for random-regression single-step genomic best linear unbiased predictor models

Random-regression models (RRM) are used in national genetic evaluations for longitudinal traits. The outputs of RRM are an index based on random regression coefficients and its reliability. The reliabilities are obtained from the inverse of the coefficient matrix of mixed model equations (MME). The reliabilities must be approximated for large data sets because it is impossible to invert the MME. There is no extensive literature on methods to approximate the reliabilities of RRM when genomic information is included by single-step GBLUP. We developed an algorithm to approximate such reliabilities. Our method combines the reliability of the index without genomic information with the reliability of a GBLUP model in terms of effective record contributions. We tested our algorithm in the 3-lactation model for milk yield from the Czech Republic. The data had 30 million test-day records, 2.5 million animals in the pedigree, and 54,000 genotyped animals. The correlation between our approximation and the reliabilities obtained from the inversion of the MME was 0.98, and the slope and intercept of the regression were 0.91 and 0.02, respectively. The elapsed time to approximate the reliabilities for the Czech data was 21 min.

HarvestMax: A Predictive Model for Crop Yield and Fertilizer Optimization

HarvestMax: A Predictive Model for Crop Yield and Fertilizer Optimization

Modeling and future projection of streamflow and sediment yield in a sub-basin of Euphrates River under the effect of climate change

ABSTRACT Recognizing the differential impacts of climate change across geographical scales, this study emphasizes the importance of statistical downscaling. Using Gene Expression Programming (GEP) and Linear Genetic Programming (LGP), statistical downscaling transforms broad climate trends into region-specific insights. This allowed for detailed analyses of anticipated changes in sediment yield and discharge within a Euphrates River sub-basin in Türkiye using large-scale variables from the CanESM2 model. The dataset is divided into calibration (1970–1995) and validation (1996–2005) periods. To assess the models’ accuracy, statistical measures such as RMSE, MAE, NSE, and R were used. The analysis revealed that LGP outperformed GEP in both discharge and sediment yield during validation, with RMSE = 51.79 m3/s and 4,325.66 tons/day, MAE = 27.14 m3/s and 1,593.34 tons/day, NSE = 0.684 and 0.627, and R = 0.841 and 0.788, respectively. However, when simulating future periods based on the observed period (2006–2020), the GEP model was superior to LGP under RCP2.6, RCP4.5, and RCP 8.5 scenarios from CanESM2. In 2021–2100, models suggest a moderate decrease in discharge and sediment yield, indicating potential shifts in the basin's hydrodynamics. These changes could disrupt hydropower generation, challenge water management practices, and alter riverine ecosystems. The results necessitate a thorough assessment of potential ecological consequences.

Combining canopy spectral reflectance and RGB images to estimate leaf chlorophyll content and grain yield in rice

Predicting rice grain yield using multi-source remotely sensed data is crucial for improving prediction accuracy, optimizing nitrogen management, and advancing precision agricultural development. However, the feasibility and reliability of using multi-source remotely sensed data to predict the grain yield remain unclear. Therefore, this study aimed to explore the possibility of providing rice leaf chlorophyll content (LCC) estimations and predictions of the grain yield using multi-source remotely sensed data. Two rice field experiments were conducted with various rice cultivars and nitrogen rates, and a field spectrometer and an unmanned aerial vehicle (UAV) equipped with a digital camera were employed to acquire the spectral reflectance and red–green–blue (RGB) images at the tillering, jointing, and full-heading stages. Destructive sampling was then conducted to measure the LCC and grain yield. The LCC was used as a bridge to develop remotely sensed prediction models for the grain yield. First, the linear relationship between grain yield and the LCC was determined at the tillering, jointing, and full-heading stages. A multiple linear regression (MLR) model was then developed to predict grain yield using multi-temporal LCCs at three growth stages. Second, multiple stepwise regression, support vector regression, and back propagation neural network were used to evaluate the estimation performance of spectral reflectance, RGB image data, and their combination for LCC. Third, the most accurate LCC estimation model was selected and coupled with the linear and MLR models of grain yield. The results showed that grain yield was significantly and positively related to the LCC at the tillering, jointing, and full-heading stages, and that the MLR model of grain yield achieved the best estimation accuracy using multi-temporal LCCs. The fusion models established by combining spectral reflectance and RGB image data improved LCC estimation accuracies. Using multi-growth stages, the most accurate predictions of grain yield were obtained from LCC estimation models (R2 = 0.698, RMSE = 0.742 t ha−1, rRMSE = 9.004 %) compared to those using single growth stages. Our study concluded that multi-source remotely sensed data fused from ground-based spectral reference and UAV-based RGB images can better predict and explain the grain yield for both single and multi-growth stages. This study provides a novel method of estimating the crop chlorophyll content and grain yield.

Water, nitrogen, and phosphorus coupling improves gray jujube fruit quality and yield.

Irrigation and fertilization are indispensable links in the jujube planting industry in southern Xinjiang, China. Regulating the relationship between fertilization and irrigation can effectively reduce costs and improve economic efficiency. A 2-year water and fertilizer optimization coupling test was conducted to determine the optimal water and nutrient supply scheme. The three-factor randomized block experiment included water (W), nitrogen (N), and phosphorus (P). According to the principal component analysis of each index, each treatment's comprehensive score was obtained. Using yield and economic regression models, the theoretical value and yield value of the optimal economic benefit are inferred. When W, N, and P were applied together, the fruit quality and yield of each treatment significantly differed, and the vitamin C, soluble sugar, and sugar-acid ratio increased significantly with an increase in N fertilizer. However, the titratable acid decreased. An increase in irrigation and nitrogen application significantly increased fruit yield. The comprehensive score was the highest in the N4P3W2 treatment, which improved fruit quality, and the lowest in the N3P3W2 treatment. When the amounts of N, P, and W were 275.56 kg hm-2, 413. 66 kg hm-2, and 7278.19 m3 hm-2, respectively, the theoretical economic benefit was the best. The N4P3W2 treatment is the optimal treatment.

Combining performances of E(m)-corrected LII and absorption for in situ measurements of the volume fraction of 2–4 nm soot particles.

Determining the soot volume fraction (fv) in combustion environments requires detailed knowledge of the optical properties of the soot particles, and in particular of their absorption function E(m). This study addresses a fundamental lack of information on the optical properties of 2–4 nm soot particles. Recent works based on the modeling of the photoelectron emission yields and UV-vis-NIR-absorption measurements found a sharp decrease of E(m) with the particle size in the vis-NIR spectral region, which is inconsistent with the in situ detection of 2–4 nm particles in the near-infrared region by laser-induced incandescence (LII) or sensitive absorption methods like cavity ring-down extinction (CRDE). The objective of this study is twofold: first, an original method for the determination of E(m) of soot particles, including 2–4 nm particles is proposed. Then, the dynamic of two widespread in situ diagnostics, LII and CRDE, are compared over three orders of magnitude of fv in atmospheric premixed ethylene/air flames with different flow rates and C/O. The determination of the absolute value of E(m) and of its variation in the flames is derived from an original analysis, which does not require complex LII modeling. This analysis is based on the comparison between the experimental and calculated LII/LIImax signals in the low fluence regime, LIImax being the plateau value of the fluence curve, which is reached at fluence larger than 1 J/cm2 for the smallest C/O. E(m) is found to vary between 0.15 at low C/O up to 0.36 for the richest flames. Concerning the comparison of the dynamics of LII and CRDE, an excellent agreement is found above a threshold (C/O)limit, while LII exhibits a stronger decrease with C/O below (C/O)limit. This discrepancy is attributed to the spectral dependence of E(m) which is negligible above (C/O)limit, but increases when C/O decreases below (C/O)limit. The particle size distribution function (PSD), measured by scanning mobility particle sizing, reveals monomodal or bimodal PSDs with soot having mobility diameter in the range 2.3–7.5 nm depending on the flame conditions. It is suggested that the particles contained in the first PSD mode, which is dominant in the low C/O range, could be affected by a significant spectral dependence of E(m) in comparison with the second PSD mode.

Optical versus radiographic imaging and tomography: introduction to the ROADS feature issue

Optical imaging is an ancient branch of imaging dating back to thousands of years. Radiographic imaging and tomography (RadIT), including the first use of X-rays by Wilhelm Röntgen, and then, γ-rays, energetic charged particles, neutrons, etc. are about 130 years young. The synergies between optical and radiographic imaging can be cast in the framework of these building blocks: Physics, Sources, Detectors, Methods, and Data Science, as described in Appl. Opt. 61, RDS1 (2022)APOPAI0003-693510.1364/AO.455628. Optical imaging has expanded to include three-dimensional (3D) tomography (including holography), due in to part the invention of optical (including infrared) lasers. RadIT are intrinsically 3D because of the penetrating power of ionizing radiation. Both optical imaging and tomography (OIT) and RadIT are evolving into even higher dimensional regimes, such as time-resolved tomography (4D) and temporarily and spectroscopically resolved tomography (4D+). Further advances in OIT and RadIT will continue to be driven by desires for higher information yield, higher resolutions, and higher probability models with reduced uncertainties. Synergies in quantum physics, laser-driven sources, low-cost detectors, data-driven methods, automated processing of data, and artificially intelligent data acquisition protocols will be beneficial to both branches of imaging in many applications. These topics, along with an overview of the Radiography, Applied Optics, and Data Science virtual feature issue, are discussed here.

Prediction Models of Growth Characteristics and Yield for Chinese Winter Wheat Based on Machine Learning

In order to eliminate the limitations of traditional winter wheat yield prediction methods, the prediction models based on machine learning are used to improve the accuracy of winter wheat yield prediction. In this study, by collecting a large amount of domestic literature about wheat growth characteristics, the irrigation amount, fertilization amount, soil nutrient status, planting density, maximum leaf area index (LAImax), maximum aboveground dry matter accumulation (Dmax) and yield (Y) were chosen to develop the learning models. Using the data of the irrigation amount, fertilization amount, soil nutrient status and planting density as the training set, the regression prediction models (Gaussian process regression mode, linear regression model, regression tree mode and support vector machine model) were used to train and learn the data of the LAImax, Dmax and Y, respectively. The results show that the Gaussian regression model has the best precision compared to the other models. The coefficients of determination (R2) of the learning results of the Gaussian regression model for the LAImax, Dmax and Y are 0.9, 0.93 and 0.86, and the root mean square error (RMSE) is 0.57, 1125.1 and 640.41. Based on the data of the irrigation amount, nitrogen application amount, potassium application amount, phosphorus application amount, organic matter content, total nitrogen content, alkali-hydrolyzable nitrogen content, available phosphorus content, available potassium content and planting density, the method proposed in this paper can reliably predict the LAImax, the Dmax and Y of winter wheat. The results also have certain reference significance for the yield prediction of other crops.

Yam Production-Related Agro-climatological Risks and Yam Yield Modeling in Côte d’Ivoire: A Review

In this paper, we present a review of the agro-climatological-related risk of yam production and models developed for yam yield prediction in Côte d’Ivoire. Four official national platforms (Ministry of Agriculture and Rural Development (MINADER), National Center for Agricultural Research (CNRA), National Agency for Rural Development Support (ANADER), Airport, Aeronautical and Meteorological Exploitation and Development Company (SODEXAM)) and six scientific search engines were investigated in this study including Theses.fr, African Journal Online, Science Direct, Google Scholar, WorldCat and Semantic Scholar. Using the boolean parameters “AND”, “OR” and “()” to facilitate and direct our search, we were able to define four key phrases comprising the topic words that were used in the search. Exclusion and inclusion criteria for the selection of documents were also defined in advance, as well as the criteria for reviewing and extracting information from selected documents. The results showed that no work in the field of agro-climatological risks related to yam production and yam yield modeling in Côte d’Ivoire was available on these online research platforms at the time of this literature review. However, other studies similar to the scope of this review on yam exist in several West African countries, particularly Ghana, Benin and Nigeria, and also in the Caribbean. These studies use simulation models such as the Approach for Land Use Sustainability (SALUS) model, the Environmental Policy Integrated Climate (EPIC) model and the Cropping Systems Simulation (CROPSYST) model for growth, yield modeling and the influence of climatic parameters on yam. In addition to these models, artificial intelligence through machine learning models was also seen in this review as an excellent tool for yield prediction for several crops including yams.

Evaluation and analysis of water-regulation value of ecosystem in Qinghai area of Qilian Mountain National Park, China

Context Water-regulation services significantly affect local social and economic development in the Qinghai area of Qilian Mountain National Park, China, and also affect the role of a ‘solid reservoir’ in China. Aim The value and change trend of water regulation was assessed through the evaluation and prediction of the water-regulation value of ecosystems. Methods InVEST water yield model and SVR model are used to evaluate and predict the water-regulation value of ecosystem in this study. Key results Grassland plays an important role in water regulation, although the area of forestland is not large, its water-regulation monetary value in 2020 accounted for 13.92% of the total evaluation value. From 2010 to 2020, the physical value of water regulation increased by 2.24% and the monetary value increased ~0.97% annually. In 2030, the amount of physical and monetary value of water regulation will be increased. Conclusion Grassland plays an important role in water regulation. It is necessary to strengthen the asset management of water regulation and optimise the ecological resources. Implications The study findings are utilised to enhance monitoring and establish ecological big-data platform, thereby elevating the quality of national park development management and decision-making services.

Yield and Energy Modeling for Biochar and Bio-Oil Using Pyrolysis Temperature and Biomass Constituents.

Pyrolysis offers a sustainable and efficient approach to resource utilization and waste management, transforming organic materials into valuable products. The quality and distribution of the pyrolysis products highly depend on the constituents' properties and set process parameters. This research aims to investigate and model this dependency, offering decision-makers a tool to guide them when designing the process for a particular application. Experimental data on the pyrolysis of various types of feedstocks processed at a wide range of pyrolysis temperatures (350-650 °C) are utilized to develop the prediction models. Four variables are modeled: the yield and energy content for both the biochar and bio-oil as a function of the pyrolysis temperature and feedstock characteristics. The models developed had very good prediction power with the coefficient of determination above 90%. The results highlight the advantages of food waste (leftover) as a suitable feedstock to produce biochar at the pyrolysis temperature within the range of 450-550 °C. Furthermore, the biofuels produced from food waste are found to be of good quality, with the bio-oil exceptionally high in energy content (HHV = 34.6 MJ/kg), which is almost 80% of that of diesel. The developed models provide a tool for predicting the biofuel yield and quality based on the feedstock selection and process temperature.

Representation of regeneration dynamics in growth and yield models: a review

Models of forest regeneration dynamics have been less widely applied in forest management than those representing growth and mortality in later stages of stand development, in spite of the critical role of regeneration in maintaining forest ecosystems. This omission is demonstrated by a review of pertinent literature and examined in the context of reforestation in the province of Alberta. Regeneration assessments in Alberta are undertaken before the regeneration phase of stand development is complete. As a result, existing growth and yield models, used to predict whether regeneration performance will meet management objectives, do not adequately represent juvenile mortality, ingress of natural regeneration, stand density, and the responses of ingress and mortality to reforestation treatments. A long-term experiment monitoring regeneration of lodgepole pine stands following harvest has over the last 20 years attempted to address some of the resulting challenges. Opportunities and needs for regeneration modelling include extension to other boreal species and ecotypes, incorporation of climatic variables, and innovations in data collection and analytical techniques. Steps are recommended for expediting the required research. 

Inflation Expectations, Liquidity Premia and Global Spillovers in Japanese Bond Markets

We provide market-based estimates of Japanese inflation expectations using an arbitrage-free dynamic term structure model of nominal and real yields that accounts for liquidity premia and the deflation protection afforded by Japanese inflation-indexed bonds, known as JGBi’s. We find that JGBi liquidity premia exhibit significant variation, and even switch sign. Properly accounting for them significantly lowers the estimated value of the indexed bonds’ deflation protection and affects inflation risk premium estimates. After liquidity adjustment, long-term Japanese inflation expectations have remained relatively stable at levels modestly exceeding one percent during the pandemic period. We then utilize our estimated liquidity measure to confirm the existence of statistically significant and economically meaningful spillovers to the JGBi market from global bond market illiquidity, as proxied by periods of low U.S. Treasury market depth.