mean bias error
Recently Published Documents





2022 ◽  
Vol 14 (2) ◽  
pp. 384
Ruixue Zhao ◽  
Tao He

Although ultraviolet-B (UV-B) radiation reaching the ground represents a tiny fraction of the total solar radiant energy, it significantly affects human health and global ecosystems. Therefore, erythemal UV-B monitoring has recently attracted significant attention. However, traditional UV-B retrieval methods rely on empirical modeling and handcrafted features, which require expertise and fail to generalize to new environments. Furthermore, most traditional products have low spatial resolution. To address this, we propose a deep learning framework for retrieving all-sky, kilometer-level erythemal UV-B from Moderate Resolution Imaging Spectroradiometer (MODIS) data. We designed a deep neural network with a residual structure to cascade high-level representations from raw MODIS inputs, eliminating handcrafted features. We used an external random forest classifier to perform the final prediction based on refined deep features extracted from the residual network. Compared with basic parameters, extracted deep features more accurately bridge the semantic gap between the raw MODIS inputs, improving retrieval accuracy. We established a dataset from 7 Surface Radiation Budget Network (SURFRAD) stations and 1 from 30 UV-B Monitoring and Research Program (UVMRP) stations with MODIS top-of-atmosphere reflectance, solar and view zenith angle, surface reflectance, altitude, and ozone observations. A partial SURFRAD dataset from 2007–2016 trained the model, achieving an R2 of 0.9887, a mean bias error (MBE) of 0.19 mW/m2, and a root mean square error (RMSE) of 7.42 mW/m2. The model evaluated on 2017 SURFRAD data shows an R2 of 0.9376, an MBE of 1.24 mW/m2, and an RMSE of 17.45 mW/m2, indicating the proposed model accurately generalizes the temporal dimension. We evaluated the model at 30 UVMRP stations with different land cover from those of SURFRAD and found most stations had a relative RMSE of 25% and an MBE within ±5%, demonstrating generalization in the spatial dimension. This study demonstrates the potential of using MODIS data to accurately estimate all-sky erythemal UV-B with the proposed algorithm.

2022 ◽  
Vol 53 (2) ◽  
pp. 119-126
R. K. MALL ◽  

Actual evapotranspiration of wheat crop during different year from 1978-79 to 1992-93 was measured daily in Varanasi, Uttar Pradesh using lysimeter. In this study three evapotranspiration computing models namely Doorenbos and Pruitt, Thornthwaite and Soil Plant Atmosphere Water (SPAW) have been used. Comparisons of these three methods show that the SPAW model is better than the other two methods for evapotraspiration estimation. In the present study the MBE (Mean-Bias-Error), RMSE (Root Mean Square Error) and t-statistic have also been obtained for better evaluations of a model performance.

2022 ◽  
Vol 12 ◽  
Ryo Fujiwara ◽  
Hiroyuki Nashida ◽  
Midori Fukushima ◽  
Naoya Suzuki ◽  
Hiroko Sato ◽  

Evaluation of the legume proportion in grass-legume mixed swards is necessary for breeding and for cultivation research of forage. For objective and time-efficient estimation of legume proportion, convolutional neural network (CNN) models were trained by fine-tuning the GoogLeNet to estimate the coverage of timothy (TY), white clover (WC), and background (Bg) on the unmanned aerial vehicle-based images. The accuracies of the CNN models trained on different datasets were compared using the mean bias error and the mean average error. The models predicted the coverage with small errors when the plots in the training datasets were similar to the target plots in terms of coverage rate. The models that are trained on datasets of multiple plots had smaller errors than those trained on datasets of a single plot. The CNN models estimated the WC coverage more precisely than they did to the TY and the Bg coverages. The correlation coefficients (r) of the measured coverage for aerial images vs. estimated coverage were 0.92–0.96, whereas those of the scored coverage by a breeder vs. estimated coverage were 0.76–0.93. These results indicate that CNN models are helpful in effectively estimating the legume coverage.

2022 ◽  
Vol 26 (1) ◽  
pp. 64-78
Mawj M. Abbas ◽  
Dhiaa H. Muhsen ◽  

In this paper, an improved hybrid algorithm called differential evolution with integrated mutation per iteration (DEIM) is proposed to extract five parameters of single-diode PV module model obtained by combining differential evolution (DE) algorithm and electromagnetic-like (EML) algorithm. The EML algorithm's attraction-repulsion idea is employed in DEIM in order to enhance the mutation process of DE. The proposed algorithm is validated with other methods using experimental I-V data. The results of presented method reveal that simulated I-V characteristics have a high degree of agreement with experimental ones. The proposed model has an average root mean square error of 0.062A, an absolute error of 0.0452A, a mean bias error of 0.006A, a coefficient of determination of 0.992, a standard test deviation around 0.04540, and 15.33sec as execution time. The results demonstrate that the proposed method is better in terms of the accuracy and execution time (convergence) when compared with other methods where provide less errors.

Energies ◽  
2021 ◽  
Vol 15 (1) ◽  
pp. 239
Koldobika Martin-Escudero ◽  
Garazi Atxalandabaso ◽  
Aitor Erkoreka ◽  
Amaia Uriarte ◽  
Matteo Porta

One of the most important steps in the retrofitting process of a building is to understand its pre-retrofitting stage energy performance. The best choice for carrying this out is by means of a calibrated building energy simulation (BES) model. Then, the testing of different retrofitting solutions in the validated model allows for quantifying the improvements that may be obtained, in order to choose the most suitable solution. In this work, based on the available detailed building drawings, constructive details, building operational data and the data sets obtained on a minute basis (for a whole year) from a dedicated energy monitoring system, the calibration of an in-use office building energy model has been carried out. It has been possible to construct a detailed white box model based on Design Builder software. Then, comparing the model output for indoor air temperature, lighting consumption and heating consumption against the monitored data, some of the building envelope parameters and inner building inertia of the model were fine tuned to obtain fits fulfilling the ASHRAE criteria. Problems found during this fitting process and how they are solved are explained in detail. The model calibration is firstly performed on an hourly basis for a typical winter and summer week; then, the whole year results of the simulation are compared against the monitored data. The results show a good agreement for indoor temperature, lighting and heating consumption compared with the ASHRAE criteria for the mean bias error (MBE).

Maicon Sérgio Nascimento dos Santos ◽  
Isac Aires de Castro ◽  
Carolina Elisa Demaman Oro ◽  
Giovani Leone Zabot ◽  
Marcus Vinícius Tres

The FAO56 Penman-Monteith model is globally accepted for the accurate determination of reference evapotranspiration (ETo). However, a lack of appropriate data encouraged the improved model’s approach to estimate ETo. This study compared the performance of 10 empirical models of ETo estimation (Penman, Priestley & Taylor, Tanner & Pelton, Makkink, Jensen & Haise, Hargreaves & Samani, Camargo, Benevides & Lopes, Turc, and Linacre) contrasted with the FAO56 model in two regions in Southern Brazil. Data were collected from automatic stations of the Brazilian National Institute of Meteorology (INMET) from December 21, 2019, to February 28, 2021. The determination coefficient (R²), mean square error (nRMSE), mean bias error (MBE), Willmott index (d), and Pearson’s correlation coefficient (r), clustering, and Principal Component Analysis (PCA) were performed. For the different regions, the radiation-based model proposed by Penman was the best alternative for estimating ETo. The model showed the most appropriated values for R2 (0.9015) and r (0.9494). The clustering and PCA analyses indicated the interrelations of the meteorological data and the combination of the models according to the parameters used for the determination of ETo.

B.I. Basok ◽  
M.P Novitska ◽  
O.M. Nedbailo ◽  
M.V Tkachenko ◽  
I.K. Bozhko

The work aim is to predict the thermal state of the air-ground heat exchanger based on an artificial neural network. Training, testing and validation of the proposed model were made on experimental data obtained in the thermophysical laboratory of the Institute of Engineering Thermophysics of the National Academy of Sciences of Ukraine. A simple neural network is used in this work. The air temperature at the inlet to the heat exchanger, and its relative humidity are selected as input parameters for the neural network. The MATLAB (R2016a) and Levenberg-Markwatt model were used in this article's calculations. One hidden layer and 10 neurons were presented in the model. The array of analysed data was divided into ratios of 70%, 15%, 15% for neural network training, validation and testing, respectively. As a result, it is obtained that the forecasting takes place with acceptable accuracy in all models. The root mean square error for the whole data set for different models varies from 0.105 to 2.323°С. The maximum mean absolute percentage error was the largest for CFD model and was 11.2%. The minimum mean bias error of the predicted data from the experimentally measured ones was found in the model using temperature, humidity, and air temperature at the outlet of the air-ground heat exchanger for the previous hour and was 0.02%. The training and testing of the proposed models based on an artificial neural network are satisfactory enough to predict the temperature taking into account the influence of weather conditions. Artificial neural networks can be used to predict the thermal state of the air-ground heat exchanger. Data representing the description of a real system are required for forecasting the parameters based on the ANN.

2021 ◽  
Vol 13 (24) ◽  
pp. 5107
Xinran Xia ◽  
Disong Fu ◽  
Ye Fei ◽  
Wei Shao ◽  
Xiangao Xia

Quantification of uncertainties associated with satellite precipitation products is a prior requirement for their better applications in earth science studies. An improved scheme is developed in this study to decompose mean bias error (MBE) and mean square error (MSE) into three components, i.e., MBE and MSE associated hits, missed precipitation, and false alarms, respectively, which are weighted by their relative frequencies of occurrence (RFO). The trend of total MBE or MSE is then naturally decomposed into six components according to the chain rule for derivatives. Quantitative estimation of individual contributions to total MBE and MSE is finally derived. The method is applied to validation of Integrated MultisatellitE Retrievals for GPM (IMERG) in Mainland China. MBE associated with false alarms is an important driver for total MBE, while MSE associated with hits accounts for more than 85% of MSE, except in inland semi-arid area. The RFO of false alarms increases, whereas the RFO of missed precipitation decreases. Both factors lead in part to a growing trend for total MBE. Detection of precipitation should be improved in the IMERG algorithm. More specifically, the priority should be to reduce false alarms.

2021 ◽  
Vasant Kearney ◽  
Alfa-Ibrahim M. Yansane ◽  
Ryan G. Brandon ◽  
Ram Vaderhobli ◽  
Guo-Hao Lin ◽  

Abstract Deep learning algorithms has recently been used to determine clinical attachment levels (CAL) which aid in the diagnosis of periodontal disease. However, the limited field-of-view of dental bitewing x-rays poses a challenge for convolutional neural networks (CNN) because out-of-view anatomy cannot be directly considered. This study presents an inpainting algorithm using generative adversarial networks (GANs) coupled with partial convolutions to predict out-of-view anatomy to enhance CAL prediction accuracy. 80,326 images were used for training, 12,901 images were used for validation and 10,687 images were used to compare non-inpainted methods to inpainted methods for CAL predictions. Statistical analyses were conducted using mean bias error (MBE), mean absolute error (MAE) and Dunn’s pairwise test comparing CAL at p=0.05. Comparator p-values demonstrated statistically significant improvement in CAL prediction accuracy between corresponding inpainted and non-inpainted methods with a MAE of 1.04mm and 1.50mm respectively. The Dunn’s pairwise test indicated a statistically significant improvement in CAL prediction accuracy between both inpainted methods compared to their non-inpainted counterparts, with the best performing methods achieving a Dunn’s pairwise value of -63.89. This study demonstrates the superiority of using a generative adversarial inpainting network with partial convolutions to predict CAL from bitewing images.

2021 ◽  
Maxime Beaudoin-Galaise ◽  
Sylvain Jutras

Abstract. Manual measurement of snow water equivalent (SWE) is still important today for several applications such as hydrological model validation. This measurement can be performed with different types of snow tube sampler or by a snow pit. Although these methods have been performed for several decades, there is an apparent lack of information required to have a consensus regarding the best reference for “true” SWE. We define and estimate the uncertainty and measurement error of different methods of snow pits and snow samplers. Analysis was based upon measurements taken over five consecutive winters (2016–2020) from the same flat and open area. This study compares two snow pit methods and three snow samplers. In addition to including the Standard Federal sampler (SFS), this study documents the first use of two new large diameter samplers, the Hydro-Québec sampler (HQS) and Université Laval sampler (ULS). Large diameter samplers had lowest uncertainty (2.6 to 4.0 %). Snow pit methods had higher uncertainty due to instruments (7.1 to 11.4 %), close to that of the SFS (mean = 10.4 %). Given its larger collected snow volume for estimating SWE and its lower uncertainty, we posit that ULS represents the most appropriate method of reference for “true” SWE. By considering ULS as the reference in calculating mean bias error (MBE), different snow pit methods overestimated SWE by 16.6 to 26.2 %, which was much higher than SFS (8.4 %). This study suggests that large diameter samplers are the best method for estimating “true” SWE.

Sign in / Sign up

Export Citation Format

Share Document