Inputs Of Artificial Neural Network Research Articles

Load Margin Assessment of Power Systems Using Artificial Neural Network and Genetic Algorithms

The power system load margin is an index that provides information on how far the system is from a case of instability. Usually, this load margin is calculated considering voltage stability requirements but low frequency oscillation modes with low damping rates, a field of study in small-signal stability, can also compromise the proper operation of power systems and so should be considered in calculating the load margin. This paper proposes a method based on artificial neural networks (ANN) using synchronized data provided by Phasor Measurement Units to monitor the load margin of systems meeting voltage stability and small-signal stability requirements. Furthermore, a Genetic Algorithm-based approach is used to select a reduced number of buses for the ANN input layer. Results of applications of the proposed method show the applicability for real-time monitoring of the load margin.

Performance Analysis of ANN Prediction for Groundwater Level Considering Regional-Specific Influence Components.

Groundwater level (GWL) varies periodically or non-periodically with various factors including precipitation, river stage (RS) change, sea level, and dewatering activities. In this study, the effect of influence components on the prediction of GWL using an artificial neural network (ANN) was investigated. Six regions with different hydrologic and geologic conditions were collected and adopted in the investigation using various input combinations. In urban areas with a high surface paved ratio, GWL was mainly affected by RS. In rural areas, the permeability of ground showed a significant impact on GWL. For such cases, the moving average (MA) was a suitable component as it could reflect both time lag and the effect of preceding precipitation. It was shown that site-specific influence component should be firstly identified and introduced into input for more enhanced and reliable prediction of GWL using ANN. The effect of learning data length (LDL) was less significant. In urban and rural areas, the introduction of RS and MA into ANN input significantly improved the prediction performance, respectively, which was consistent with the correlation analysis of GWL influence components.

Generalized regression neural network application for fault type detection in distribution transformer windings considering statistical indices

PurposeThis study aims to use frequency response analysis, a powerful tool to detect the location and types of transformer winding faults. Proposing an effective intelligent approach for interpreting the frequency responses is the most crucial problem of this method and has created many challenges.Design/methodology/approachHeat maps based on appropriate statistical indices have been supplied to depict the variations in the frequency responses associated with each fault type, fault location and fault extent along the windings. Also, after analyzing the results of artificial neural network (ANN) techniques, the generalized regression neural network method is introduced as the most effective solution for the classification of transformer winding faults.FindingsUsing a comparative approach, the performance of the used indices and ANN techniques are evaluated. The results showed the proper performance of Lin’s concordance coefficient (LCC) index and the amplitude (Amp) part of the frequency response. The proposed fitting percentage (FP) index can assist the intelligent classifiers in diagnosing the radial deformation (RD) fault with the highest accuracy considering all frequency response components in the classification procedure of winding faults.Practical implicationsVarious ANN techniques are used to detect and determine the type of four important faults of transformer winding, i.e. axial displacement, RD, disc space variation and short circuit. Various statistical indices, such as cross-correlation factor, LCC, standard difference area, sum of errors, normalized root-mean-square deviation and FP, are used to extract the features of the frequency responses to consider as the ANN inputs. In addition, different components of the frequency response, such as Amp, argument, real and imaginary parts are examined in this paper. To implement the proposed procedure, step by step, various types of winding faults with different locations and extents are applied on the 20 kV winding of a 1.6 MVA distribution transformer.Originality/valueContributions have been made in identifying and diagnosing transformer winding defects through the use of appropriate algorithms for future research.

Epileptic seizure identification in EEG signals using DWT, ANN and sequential window algorithm

A patient-specific novel systematic methodology is described in this study for automatic seizure detection from raw electroencephalogram (EEG) signals. Filtering process by means of band-pass finite impulse response (FIR) filter with the frequency range of 0.5–40 Hz is implemented at the outset to eliminate different artifacts and noises mixed with raw EEG signals. As EEGs are highly non-linear and non-stationary signals in nature, discrete wavelet transform (DWT) is then used to analyze the signals in time-frequency domain. DWT with four level decomposition is performed using db6 mother wavelet for feature extraction. A new feature set, composed of eleven non-linear statistical features extracted from each sub-bands resulting from due to wavelet decomposition, is then fed to the input of artificial neural network (ANN) to classify the signal accurately. Finally, a novel algorithm named sequential window algorithm is carried out to improve the classification performance. 99.44% mean classification accuracy, 80.66% average sensitivity, 4.12 s mean latency and 0.2% average false positive rate (FPR) are achieved in this study. This study successfully reduces the latency time with more accuracy and significantly low FPR.

Comparison of different machine learning approaches for tropospheric profiling based on COSMIC-2 data

Precise and reliable information on the tropospheric temperature and water vapor profiles play a key role in weather and climate studies. Among the sensors supporting the observations of the troposphere, one can distinguish the Global Navigation Satellite System Radio Occultation (RO) technique, which provides accurate and high-quality meteorological profiles. However, external knowledge about temperature is essential to estimate other physical atmospheric parameters. To overcome this constraint, I trained and evaluated four different machine learning models comprising Artificial Neural Network (ANN) and Random Forest regression algorithms, where no auxiliary meteorological data is needed. To develop the models, I employed 150,000 globally distributed (45°S–45°N) RO profiles between October 2019 and December 2020. Input vectors consisted of bending angle or refractivity profiles from the Formosa Satellite-7/Constellation Observing System for Meteorology, Ionosphere, and Climate-2 mission together with the month, hour, and latitude of the RO event. While temperature, pressure, and water vapor profiles derived from the modern ERA5 reanalysis and interpolated to the RO location served as the models’ targets. Evaluation on the testing data set revealed a good agreement between all model outputs and ERA5 targets, where slightly better statistics were noted for ANN and refractivity inputs. Vertically averaged root mean square error (RMSE) did not exceed 1.7 K for the temperature and reached around 1.4 hPa and 0.45 hPa for the total and water vapor pressures. Additional validation with 477 co-located radiosonde observations and the operational one-dimensional variational product showed slightly larger discrepancies with the mean RMSE of around 1.9 K, 1.9 hPa, and 0.5 hPa for the temperature, pressure, and water vapor, respectively.Graphical

The use of deep learning algorithms to predict mechanical strain from linear acceleration and angular rates of motion recorded from a horse hoof during exercise

Mobility solutions offered by living creatures have inspired engineers to capture their locomotion patterns and then develop novel animal-like robots that use legs for locomotion. Exploring relationships amongst mechanical responses and kinematic parameters is essential for both inventing these robots and enhancing computational techniques. Establishment of accurate physical models to quantify mechanical responses of biological systems is challenging because the corresponding variables are multidimensional, dynamic and highly nonlinear. This encourages the advent of data-driven models in mechanical sciences. This paper delves into the use of feedforward and time-series (dynamic) artificial neural networks (ANN) to analyse experimental data recorded from a racing horse exercised up to 60 km/h to then relate hoof mechanical strain to kinematic parameters recorded experimentally. An inertial measurement unit that was comprised of a sensor and data acquisition system package was designed and mounted on the horse's hoof to measure linear accelerations and angular rates of motion. In addition, an instrumented Aluminium horseshoe that was designed and manufactured and contained: (1) inertial sensors including three orthogonal accelerometers and three orthogonal rate gyroscopes; and, (2) a strain gauge located at the middle of the shoe. The horse was warmed up in a steady gallop at around 35 km/h for 1 km then turned around and galloped at increasing speed to 68 km/h back to the finishing line. Nine kinematic parameters, measured during horse exercise, formed the ANNs input variables: hoof linear accelerations along three orthogonal directions (axe,ay,az), hoof angular rates of motion along three orthogonal directions (Gx, Gy, Gz), shoe linear accelerations along three orthogonal directions (axs, ays, azs), and time. Feedforward and time-series ANNs trained using 1,000,000 experimental instances offered excellent reliability for the prediction of mechanical strain from kinematic measurements, i.e. R ≥ 0.97.

Neurotic Fuzzy-Data-Envelopment Analysis to Forecast Efficiency of Bank Branches

In this study the prediction of efficiency of four different Bank Branches have been done by using Neurotic Fuzzy Data Envelopment Analysis approach. In the first stage of the study, Artificial Neural Network (ANN) model has been modelled and trained using the last five years data. The data belonging any year has been taken as input of ANN, next year data has been defined as output of ANN. Fuzzyfication process has been applied to obtained predictions based on asking managers of bank branches, after Fuzzy Data Envelopment Analysis process has been applied to fuzzy values. As a result, the bank branches parameters belonging to 2021 year have been obtained. The efficiency of 2021 for bank branches have been calculated based on Fuzzy Data Envelopment Analysis (FDEA).

Prediction of fracture parameters of concrete using an artificial neural network approach

In this study, detailed experimental results of a series of concrete fracture tests on published literatures were collected into a database named as CFT-DB. Based on large amount of experimental data, an artificial neural network (ANN) approach was employed to build connections between some influential factors and certain fracture parameters, and therefore to predict the corresponding fracture parameters. The fracture parameters investigated mainly were the initial cracking fracture toughness KIcini, the unstable fracture parameters KIcun and the fracture energy GF. They correspond to crack initiation, critical unstable crack propagation and average energy release during the complete fracture process. Results showed that ANN models have better performance than existing empirical formulas when predicting concrete fracture parameters. By adding more variables as ANN input, the accuracy of ANN models was further improved. Parametric study was then performed based the constructed ANN models to evaluate the impact of each input parameters on concrete fracture parameters. Specially, size effect of these concrete facture parameters was discussed. Research of the present paper can be seen as a summary of past researches on fracture parameters. However, it constructs prediction model with higher accuracy and deepens the understanding of influential factors on fracture parameters.

An anesthesia depth computing method study based on wavelet transform and artificial neural network

General anesthesia is an essential part of surgery to ensure the safety of patients. Electroencephalogram (EEG) has been widely used in anesthesia depth monitoring for abundant information and the ability of reflecting the brain activity. The paper proposes a method which combines wavelet transform and artificial neural network (ANN) to assess the depth of anesthesia. Discrete wavelet transform was used to decompose the EEG signal, and the approximation coefficients and detail coefficients were used to calculate the 9 characteristic parameters. Kruskal-Wallis statistical test was made to these characteristic parameters, and the test showed that the parameters were statistically significant for the differences of the four levels of anesthesia: awake, light anesthesia, moderate anesthesia and deep anesthesia ( P < 0.001). The 9 characteristic parameters were used as the input of ANN, the bispectral index (BIS) was used as the reference output, and the method was evaluated by the data of 8 patients during general anesthesia. The accuracy of the method in the classification of the four anesthesia levels of the test set in the 7:3 set-out method was 85.98%, and the correlation coefficient with the BIS was 0.977 0. The results show that this method can better distinguish four different anesthesia levels and has broad application prospects for monitoring the depth of anesthesia.

Using an Artificial Neural Network to improve operational wind prediction in a small unresolved valley

AbstractThis study improves surface wind predictions in an unresolved valley using an artificial neural network (ANN). Forecasting winds in complex terrain with a mesoscale model is challenging. This study assesses the quality of 3-km wind forecasts by the Weather Research and Forecasting (WRF) model and the potential of post-processing by an ANN within the 1-2 km wide Cadarache Valley in southeast France. Operational wind forecasts for 110m above ground level and the near-surface vertical potential temperature gradient with a lead time of 24-48h were used as ANN input. Observed horizontal wind components at 10m within the valley were used as targets during ANN training. We use the Directional ACCuracy (DACC45, wind direction error ≤ 45°) and mean absolute error to evaluate the WRF direct model output and the ANN results. By post-processing, the score for DACC45 improves from 56% in the WRF direct model output to 79% after applying the ANN. Furthermore, the ANN performed well during the day and night, but poorly during the morning and afternoon transitions. The ANN improves the DACC45 at 10m even for poor WRF forecasts (direction bias ≥ 45°) from 42% to 72%. A shorter lead time and finer grid spacing (1 km) showed negligible impact which suggests that a 3 km grid spacing and a 24-48h lead time is effective and relatively cheap to apply. We find that WRF performs well in near-neutral conditions and poorly in other atmospheric stability conditions. The ANN post-treatment consistently improves the wind forecast for all stability classes to a DACC45 of about 80%. The study demonstrates the ability to improve Cadarache valley wind forecasts using an ANN as post-processing for WRF daily forecasts.

P-105: Mass spectrometry and artificial neural networks for discrimination of extramedullary Multiple Myeloma

<h3>Background</h3> Multiple myeloma (MM) is the second most common hematological malignancy of the elderly. The bone marrow is infiltrated by malignant plasma cells. MM may progress into so-called extramedullary disease (EMD). EMD occurs when a subclone of clonal plasma cells migrates out of the bone marrow and infiltrates soft tissues. <h3>Aims</h3> We focused on the analysis of low molecular weight molecules in peripheral blood of 20 MM and 20 EMD patients using MALDI-TOF mass spectrometry to create a diagnostic tool based on prediction by artificial neural network, which should distinguish different groups of diseases. <h3>Methods</h3> Matrix-Assisted Laser Desorption/Ionization Time-of Flight Mass Spectrometry (MALDI-TOF MS) has become an indispensable research tool, which is used for analysis of biomolecules and various organic molecules. Artificial Neural Networks (ANN) are components of artificial intelligence inspired by biological neural networks. Using ANN, we can model complex non-linear systems, as previously published. In our previous study, we recorded mass spectra of MM and healthy donor samples. ANN specifically predicted MM samples with high sensitivity, specificity and accuracy. <h3>Results</h3> The RStudio was used for statistical analysis, where the data were evaluated using Principal Component Analysis (PCA) and Partial least squares discriminant analysis (PSL-DA). Using MALDI-TOF MS, it was possible to distinguish between samples of MM patients and healthy donors, as well as MM and EMD patients. Informative patterns in mass spectra served as inputs for ANN that specifically distinguished between healthy donors and patients. <h3>Conclusion</h3> We demonstrated that using MALDI-TOF MS coupled with ANN is a useful tool that can distinguish between healthy donors and patients. Thus, it can be used as a fast alternative to conventional analyses. This study was supported by grants of the Ministry of Health of the Czech Republic, grant nr. NV18-08-00299, AZV 18-03-00203.

Using radial basis function network to model the heat transfer and pressure drop of water based nanofluids containing MgO nanoparticles

Present study is focused on feasibility of predicting the thermal and fluid properties of MgO/water nanofluid using radial based function (RBF) type artificial neural networks (ANNs). To design the ANN, Reynolds number and volume fraction of nanoparticles (ϕ) were considered as ANN inputs and in principle independent parameters and on the other hand, the parameters of relative pressure drop and relative heat transfer coefficient were considered as the outputs of this ANN. One of the important innovations in the present study is the attempt to simultaneously predict the relative pressure drop as undesirable and the relative heat transfer coefficient as undesirable parameters. The designed ANN using the radial basis function (RBF) was able to predict the laboratory parameters of relative pressure drop and relative heat transfer coefficient (RHTC) with 99.3% and 99.5% accuracy, respectively. It can drastically reduce the time and financial costs of laboratory methods. Based on the obtained results in ϕ = 0.125%, the unfavorable parameter (relative pressure drop) has a significant supremacy over the optimal parameter (RHTC) and therefore the ϕ is not suitable for use in thermal cycles. But on the other hand, with ϕ = 0.5%, the optimal parameter (RHTC) has a significant supremacy over the undesirable parameter (relative pressure drop), and therefore for MgO/water nanofluid, ϕ>0.5% are suitable for using in thermal cycles.

Extraction of Phenolic Compounds with Antioxidant Activity from Strawberries: Modelling with Artificial Neural Networks (ANNs).

This research study focuses on the evaluation of the total phenolic compounds (TPC) and antioxidant activity (AOA) of strawberries according to different experimental extraction conditions by applying the Artificial Neural Networks (ANNs) technique. The experimental data were applied to train ANNs using feed- and cascade-forward backpropagation models with Levenberg-Marquardt (LM) and Bayesian Regulation (BR) algorithms. Three independent variables (solvent concentration, volume/mass ratio and extraction time) were used as ANN inputs, whereas the three variables of total phenolic compounds, DPPH and ABTS antioxidant activities were considered as ANN outputs. The results demonstrate that the best cascade- and feed-forward backpropagation topologies of ANNs for the prediction of total phenolic compounds and DPPH and ABTS antioxidant activity factors were the 3-9-1, 3-4-4-1 and 3-13-10-1 structures, with the training algorithms of trainlm, trainbr, trainlm and threshold functions of tansig-purelin, tansig-tansig-tansig and purelin-tansig-tansig, respectively. The best R2 values for the predication of total phenolic compounds and DPPH and ABTS antioxidant activity factors were 0.9806 (MSE = 0.0047), 0.9651 (MSE = 0.0035) and 0.9756 (MSE = 0.00286), respectively. According to the comparison of ANNs, the results showed that the cascade-forward backpropagation network showed better performance than the feed-forward backpropagation network for predicting the TPC, and the FFBP network, in predicting the DPPH and ABTS antioxidant activity factors, had more precision than the cascade-forward backpropagation network. The ANN technique is a potential method for estimating targeted total phenolic compounds and the antioxidant activity of strawberries.

Forecasting Water Quality Index in Groundwater Using Artificial Neural Network

Groundwater quality monitoring in the vicinity of drilling sites is crucial for the protection of water resources. Selected physicochemical parameters of waters were marked in the study. The water was collected from 19 wells located close to a shale gas extraction site. The water quality index was determined from the obtained parameters. A secondary objective of the study was to test the capacity of the artificial neural network (ANN) methods to model the water quality index in groundwater. The number of ANN input parameters was optimized and limited to seven, which was derived using a multiple regression model. Subsequently, using the stepwise regression method, models with ever fewer variables were tested. The best parameters were obtained for a network with five input neurons (electrical conductivity, pH as well as calcium, magnesium and sodium ions), in addition to five neurons in the hidden layer. The results showed that the use of the parameters is a convenient approach to modeling water quality index with satisfactory and appropriate accuracy. Artificial neural network methods exhibited the capacity to predict water quality index at the desirable level of accuracy (RMSE = 0.651258, R = 0.9992 and R2 = 0.9984). Neural network models can thus be used to directly predict the quality of groundwater, particularly in industrial areas. This proposed method, using advanced artificial intelligence, can aid in water treatment and management. The novelty of these studies is the use of the ANN network to forecast WQI groundwater in an area in eastern Poland that was not previously studied—in Lublin.

Artificial neural networks in the prediction of soil chemical attributes using apparent electrical conductivity

Aim of study: To use artificial neural networks (ANN) to predict the values and spatial distribution of soil chemical attributes from apparent soil electrical conductivity (ECa) and soil clay contents.Area of study: The study was carried out in an area of 1.2-ha cultivated with cocoa, located in the state of Bahia, Brazil.Material and methods: Data collections were performed on a sampling grid containing 120 points. Soil samples were collected to determine the attributes: clay, silt, sand, P, K+, Ca2+, Mg2+, S, pH, H+Al, SB, CTC, V, OM and P-rem. ECa was measured using the electrical resistivity method in three different periods related to soil sampling: 60 days before (60ECa), 30 days before (30ECa) and when collecting soil samples (0ECa). For the prediction of chemical and physical-chemical attributes of the soil, models based on ANN were used. As input variables, the ECa and the clay contents were used. The quality of ANN predictions was determined using different statistical indicators. Thematic maps were constructed for the attributes determined in the laboratory and those predicted by the ANNs and the values were grouped using the fuzzy k-means algorithm. The agreement between classes was performed using the kappa coefficient.Main results: Only P and K+ attributes correlated with all ANN input variables. ECa and clay contents in the soil proved to be good variables for predicting soil attributes.Research highlights: The best results in the prediction process of the P and K+ attributes were obtained with the combination of ECa and the clay content.

Discriminating chaotic and stochastic time series using permutation entropy and artificial neural networks

Extracting relevant properties of empirical signals generated by nonlinear, stochastic, and high-dimensional systems is a challenge of complex systems research. Open questions are how to differentiate chaotic signals from stochastic ones, and how to quantify nonlinear and/or high-order temporal correlations. Here we propose a new technique to reliably address both problems. Our approach follows two steps: first, we train an artificial neural network (ANN) with flicker (colored) noise to predict the value of the parameter, alpha, that determines the strength of the correlation of the noise. To predict alpha the ANN input features are a set of probabilities that are extracted from the time series by using symbolic ordinal analysis. Then, we input to the trained ANN the probabilities extracted from the time series of interest, and analyze the ANN output. We find that the alpha value returned by the ANN is informative of the temporal correlations present in the time series. To distinguish between stochastic and chaotic signals, we exploit the fact that the difference between the permutation entropy (PE) of a given time series and the PE of flicker noise with the same alpha parameter is small when the time series is stochastic, but it is large when the time series is chaotic. We validate our technique by analysing synthetic and empirical time series whose nature is well established. We also demonstrate the robustness of our approach with respect to the length of the time series and to the level of noise. We expect that our algorithm, which is freely available, will be very useful to the community.

Preliminary study on PFC3D microparameter calibration using optimization of an artificial neural network

Microparameter calibration for matching macroscopic responses of particle flow code 3D (PFC3D) models is generally conducted through trial-and-error which is inefficient and time-consuming. Several automatic calibration methods have been proposed but they are still limitations in the number of calibratable microparameters, range of macroscopic responses and degree of freedom in user-defined constraints. To overcome such limitations, a novel calibration method is proposed utilizing the constrained optimization of an artificial neural network (ANN). The ANN is trained with 600 PFC3D simulations to predict the unconfined compressive strength (UCS), Young’s modulus (E) and Poisson’s ratio (v) of a PFC3D model for a given set of 15 microparameter values. Unlike other ANN-based DEM calibration methods, the proposed method calibrates microparameters by optimizing the ANN inputs rather than obtaining the calibrated values as the ANN outputs. The integration of a PFC3D-mimicking ANN with constrained optimization enables microparameter calibration for a wider range of microparameters, macroscopic responses and a higher degree of freedom in user-defined constraints.

Development of a method for assessment and forecasting of the radio electronic environment

Decision making support systems (DSS) are actively used in all spheres of human life. The system of the electronic environment analysis is not an exception. However, there are a number of problems in the analysis of the electronic environment, for example: the signals are analyzed in a complex electronic environment against the background of intentional and natural interference. Input signals do not match the standards, and their interpretation depends on the experience of the operator (expert), the completeness of additional information on a particular task (uncertainty condition). The best solution in this situation is found in the integration with the data of the information system analysis of the electronic environment, artificial neural networks and fuzzy cognitive models. Their advantages are also the ability to work in real time and quick adaptation to specific situations. The article develops a method for assessing and forecasting the electronic environment.&#x0D; Improving the efficiency of evaluation information processing is achieved through the use of evolving neuro-fuzzy artificial neural networks; learning not only the synaptic weights of the artificial neural network, the type and parameters of the membership function. The efficiency of information processing is also achieved through training in the architecture of artificial neural networks; taking into account the type of uncertainty of the information that has to be assessed; synthesis of rational structure of fuzzy cognitive model. It reduces the computational complexity of decision-making; has no accumulation of learning error of artificial neural networks as a result of processing the information coming to the input of artificial neural networks. The example of assessing the state of the electronic environment showed an increase in the efficiency of assessment at the level of 15–25 % on the efficiency of information processing

Modeling Agrobacterium-Mediated Gene Transformation of Tobacco (Nicotiana tabacum)-A Model Plant for Gene Transformation Studies.

The multilayer perceptron (MLP) topology of an artificial neural network (ANN) was applied to create two predictor models in Agrobacterium-mediated gene transformation of tobacco. Agrobacterium-mediated transformation parameters, including Agrobacterium strain, Agrobacterium cell density, acetosyringone concentration, and inoculation duration, were assigned as inputs for ANN–MLP, and their effects on the percentage of putative and PCR-verified transgenic plants were investigated. The best ANN models for predicting the percentage of putative and PCR-verified transgenic plants were selected based on basic network quality statistics. Ex-post error calculations of the relative approximation error (RAE), the mean absolute error (MAE), the root mean square error (RMS), and the mean absolute percentage error (MAPE) demonstrated the prediction quality of the developed models when compared to stepwise multiple regression. Moreover, significant correlations between the ANN-predicted and the actual values of the percentage of putative transgenes (R2 = 0.956) and the percentage of PCR-verified transgenic plants (R2 = 0.671) indicate the superiority of the established ANN models over the classical stepwise multiple regression in predicting the percentage of putative (R2 = 0.313) and PCR-verified (R2= 0.213) transgenic plants. The best combination of the multiple inputs analyzed in this investigation, to achieve maximum actual and predicted transgenic plants, was at OD600 = 0.8 for the LB4404 strain of Agrobacterium × 300 μmol/L acetosyringone × 20 min immersion time. According to the sensitivity analysis of ANN models, the Agrobacterium strain was the most important influential parameter in Agrobacterium-mediated transformation of tobacco. The prediction efficiency of the developed model was confirmed by the data series of Agrobacterium-mediated transformation of an important medicinal plant with low transformation efficiency. The results of this study are pivotal to model and predict the transformation of other important Agrobacterium-recalcitrant plant genotypes and to increase the transformation efficiency by identifying critical parameters. This approach can substantially reduce the time and cost required to optimize multi-factorial Agrobacterium-mediated transformation strategies.

Potential of water balance and remote sensing-based evapotranspiration models to predict yields of spring barley and winter wheat in the Czech Republic

Indicators based on evapotranspiration (ET) provide useful information about surface water status, response of vegetation to drought stress, and potential growth limitations. The capability of ET-based indicators, including actual ET and the evaporative stress index (ESI), to predict crop yields of spring barley and winter wheat was analyzed for 33 districts of the Czech Republic. In this study, the ET-based indicators were computed using two different approaches: (i) a prognostic model, SoilClim, which computes the water balance based on ground weather observations and information about soil and land cover; (ii) the diagnostic Atmosphere–Land Exchange Inverse (ALEXI) model based primarily on remotely sensed land surface temperature data. The capability of both sets of indicators to predict yields of spring barley and winter wheat was tested using artificial neural networks (ANNs) applied to the adjusting number and timeframe of inputs during the growing season. Yield predictions based on ANNs were computed for both crops for all districts together, as well as for individual districts. The root mean square error (RMSE) and coefficient of determination (R2) between observed and predicted yields varied with date within the growing season and with the number of ANN inputs used for yield prediction. The period with the highest predictive capability started from early-June to mid-June. This optimal period for yield prediction was identifiable already at the lower number of ANN inputs, nevertheless, the accuracy of the prediction improved as more inputs were included within ANNs.The RMSE values for individual districts varied between 0.4 and 0.7 t ha–1 while R2 reached values of 0.5–0.8 during the optimal period. Results of the study demonstrated that ET-based indicators can be used for yield prediction in real time during the growing season and therefore have great potential for decision making at regional and district levels.