Set Of Input Variables Research Articles

Optimization of Factorial Design with the type of Plackett-Burman Design to Study the Effects of Organic Rice Production Process: First Step Experiment

The research aims at the optimization to determine factors production process of the of the output organic rice so that the best possible set of parameters affecting it can be selected to get the desired output. For this purpose, the effect of various parameters on the organic rice output is studied. To facilitate the study and detailed analysis, a statistical model is constructed which is used to predict and optimize the performance of the system. Efficient organic rice optimization determines the input variable settings to adjust the organic rice of the organic rice according to the consumption of the parts in the next phase of production process.To study the interaction among the factors a 36 factorial experiment approach has been adopted using the two basic principles of experimental design replication and randomization. The process model was formulated based on analysis of variance (ANOVA) and regression of coefficient using Minitab Release 19.00. The output is represented graphically and in the form of empirical model which defines the performance characteristics of the production process of organic rice by factorial design type of Placket-Burman design

Machine-learning methods for stream water temperature prediction

Abstract. Water temperature in rivers is a crucial environmental factor with the ability to alter hydro-ecological as well as socio-economic conditions within a catchment. The development of modelling concepts for predicting river water temperature is and will be essential for effective integrated water management and the development of adaptation strategies to future global changes (e.g. climate change). This study tests the performance of six different machine-learning models: step-wise linear regression, random forest, eXtreme Gradient Boosting (XGBoost), feed-forward neural networks (FNNs), and two types of recurrent neural networks (RNNs). All models are applied using different data inputs for daily water temperature prediction in 10 Austrian catchments ranging from 200 to 96 000 km2 and exhibiting a wide range of physiographic characteristics. The evaluated input data sets include combinations of daily means of air temperature, runoff, precipitation and global radiation. Bayesian optimization is applied to optimize the hyperparameters of all applied machine-learning models. To make the results comparable to previous studies, two widely used benchmark models are applied additionally: linear regression and air2stream. With a mean root mean squared error (RMSE) of 0.55 ∘C, the tested models could significantly improve water temperature prediction compared to linear regression (1.55 ∘C) and air2stream (0.98 ∘C). In general, the results show a very similar performance of the tested machine-learning models, with a median RMSE difference of 0.08 ∘C between the models. From the six tested machine-learning models both FNNs and XGBoost performed best in 4 of the 10 catchments. RNNs are the best-performing models in the largest catchment, indicating that RNNs mainly perform well when processes with long-term dependencies are important. Furthermore, a wide range of performance was observed for different hyperparameter sets for the tested models, showing the importance of hyperparameter optimization. Especially the FNN model results showed an extremely large RMSE standard deviation of 1.60 ∘C due to the chosen hyperparameters. This study evaluates different sets of input variables, machine-learning models and training characteristics for daily stream water temperature prediction, acting as a basis for future development of regional multi-catchment water temperature prediction models. All preprocessing steps and models are implemented in the open-source R package wateRtemp to provide easy access to these modelling approaches and facilitate further research.

Forecasting of Heat Production in Combined Heat and Power Plants Using Generalized Additive Models

The paper presents a developed methodology of short-term forecasting for heat production in combined heat and power (CHP) plants using a big data-driven model. An accurate prediction of an hourly heat load in the day-ahead horizon allows a better planning and optimization of energy and heat production by cogeneration units. The method of training and testing the predictive model with the use of generalized additive model (GAM) was developed and presented. The weather data as an input variables of the model were discussed to show the impact of weather conditions on the quality of predicted heat load. The new approach focuses on an application of the moving window with the learning data set from the last several days in order to adaptively train the model. The influence of the training window size on the accuracy of forecasts was evaluated. Different versions of the model, depending on the set of input variables and GAM parameters were compared. The results presented in the paper were obtained using a data coming from the real district heating system of a European city. The accuracy of the methods during the different periods of heating season was performed by comparing heat demand forecasts with actual values, coming from a measuring system located in the case study CHP plant. As a result, a model with an averaged percentage error for the analyzed period (November–March) of less than 7% was obtained.

Combining texture, color, and vegetation indices from fixed-wing UAS imagery to estimate wheat growth parameters using multivariate regression methods

Precision crop management in modern agriculture requires timely and effective acquisition of crop growth information. Recently, unmanned aerial systems (UASs) have rapidly developed and are now widely used in crop remote sensing (RS). Vegetation index (VI) and color index (CI) are commonly used RS methods to monitor crops. Texture is intrinsic information of the images, which can reflect the crop canopy structure and be used for vegetation classification. The objective of this study was to explore the potential of combining VI, CI, and texture to improve the estimation accuracy of wheat growth parameters based on fixed-wing UAS imagery. Wheat field experiments were carried out at the Xinghua Experimental Station for two consecutive years of 2017–2019 on three wheat cultivars under five nitrogen fertilization rates. Two commonly used wheat growth parameters, leaf area index (LAI) and leaf dry matter (LDM), synchronized with wheat field UAS images, were obtained at key growth stages. Simple regression (SR) was used to determine quantitative relationships between RS variables (VI, CI, and texture) and LAI, LDM. The data showed that individual texture does not correlate well with wheat growth parameters, while a texture index (TI), containing two texture measurements, showed stronger correlation with LAI and LDM. With the utilization of simple regression (SR), VI (R2 > 0.65, RRMSE < 21.87%) exhibited the best accuracy in estimating LAI and LDM, followed by TI (R2 > 0.51, RRMSE < 26.28%) and CI (R2 > 0.34, RRMSE < 27.74%). Multiple linear regression (MLR) and random forest (RF) were further employed to develop LAI and LDM estimation models using different input variable sets (VIs, VIs + CIs, and VIs + CIs + TIs). Compared with SR and MLR, the RF models that combined VIs, CIs, and TIs greatly improved the estimation accuracy of LAI and LDM, and the validated R2 of the best RF models for LAI and LDM estimation reached 0.78 and 0.78 (RRMSE = 17.32% and 13.83%) in pre-heading stages, 0.81 and 0.77 (RRMSE = 17.86% and 16.08%) in post-heading stages, and 0.76 and 0.75 (RRMSE = 18.13% and 16.79%) in all stages, respectively. This study demonstrated that image textures can assist wheat monitoring to achieve higher estimation accuracy of LAI and LDM, and fixed-wing UAS is a promising platform that can provide reliable data for large-scale crop management.

Optimization of pulp and acid leaching operations in zinc ingot production process with the data mining approach

This study presents a data mining approach to optimize the chemical processes. Typically, these processes are affected by a variety of interactive variables. So, their quality monitoring and detection usually emphasize changing main variables and their interaction effects. Sometimes, the input to the chemical processes lacks access to the raw materials, which causes the manufacturers to use residue instead of high-quality materials. The use of residue has flaws, most notably the low quality of the process output. In this paper, calculating the optimum points of process variables using residue with the data mining approach is suggested. As a real case, one of the operations of the zinc ingot production process, i.e., pulp and acid leaching operations, are studied. In this way, first, by studying the operation in detail, the required data are collected, and key input and output variables are distinguished. Then, by data pre-processing, the optimum points of the process are determined using data mining algorithms. Therefore, the input variable settings of the operation are extracted to optimize the output variables. To validate the results, a set of test data are used to examine the two periods before and after the variable settings. The results show that the operation output is improved significantly. According to the robustness of the proposed method, it can be used as a benchmark for other chemical processes.

Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model

The spatial coverage of satellite aerosol classification was improved using a random forest (RF) model trained with observational data including target (aerosol type) and input (satellite measurement) variables. The AErosol RObotic NETwork (AERONET) aerosol-type dataset was used for the target variables. Satellite input variables with many missing data or low mean-decrease accuracy were excluded from the final input variable set, and good performance in aerosol-type classification was achieved. The performance of the RF-based model was evaluated on the basis of the wavelength dependence of single-scattering albedo (SSA) and fine-mode-fraction values from AERONET. Typical SSA wavelength dependence for individual aerosol types was consistent with that obtained for aerosol types by the RF-based model. The spatial coverage of the RF-based model was also compared with that of previously developed models in a global-scale case study. The study demonstrates that the RF-based model allows satellite aerosol classification with improved spatial coverage, with a performance similar to that of previously developed models.

Ground movements induced by installation of twin large diameter deeply-buried caissons: 3D numerical modeling

The assessment and control of ground movements during the installation of large diameter deeply-buried (LDDB) caissons are critically important to maintain the stability of surrounding infrastructures. However, for twin LDDB caissons which have been installed worldwide, no well-documented guidelines for assessing the induced ground movements are available due to the complexities of caisson–soil interaction. To this end, considering the mechanical boundaries of caissons and mechanized installation process, this paper presents a simple kinematic mechanical model balancing both computational cost and accuracy, which can be easily incorporated in commercial finite-element (FE) programs. Based on a project of twin LDDB caissons alternately installed employing a newly developed installation technology in wet ground with stiff clays in Zhenjiang, China, a three-dimensional (3D) numerical model is developed to capture the ground movements in terms of surface settlements and radial displacements induced by the installation of twin LDDB caissons. Moreover, hardening soil model with small-strain stiffness (HSSmall model) conceptually capable of capturing the nonlinear soil stiffness from very small to large strain levels is used to simulate undrained ground. The validations against field observations, empirical predictions and centrifuge test data are carried out to demonstrate the accuracy and validity of the developed FE model. Subsequently, the comparisons of ground movements numerically obtained in three frequently used installation schemes (i.e., synchronous, asynchronous and alternating installation) are conducted for installation sequence optimization of twin caissons. It is found that synchronous installation is the optimal scheme for limiting ground movements. Parametric studies considering the effects of horizontal spacing between twin caissons, staged penetration depth, inner diameter, controllable soil-plugging height, frictional coefficient between caisson–soil interface, as well as cutting edge gradient are thus performed in synchronous installation scheme. Based on an artificial data set generated through FE calculation, the multivariate adaptive regression splines (MARS) model capable of accurately capturing the nonlinear relationships between a set of input variables and output variables in multi-dimensions is used to analyze the sensitivity of caisson design parameters. Finally, the MARS mathematical equations for predicting the maximum surface settlement and radial displacement used in preliminary caisson design are proposed.

A Global Sensitivity Analysis Method for Multi-Input Multi-Output System and its Application in Structural Design

Commonly, variance-based global sensitivity analysis methods are popular and applicable to quantify the impact of a set of input variables on output response. However, for many engineering practical problems, the output response is not single but multiple, which makes some traditional sensitivity analysis methods difficult or unsuitable. Therefore, a novel global sensitivity analysis method is presented to evaluate the importance of multi-input variables to multi-output responses. First, assume that a multi-input multi-output system (MIMOS) includes [Formula: see text] variables and [Formula: see text] responses. A set of summatory functions [Formula: see text] and [Formula: see text] are constructed by the addition and subtraction of any two response functions. Naturally, each response function is represented using a set of summatory function. Subsequently, the summatory functions [Formula: see text] and [Formula: see text] are further decomposed based on the high dimensional model representation (HDMR), respectively. Due to the orthogonality of all the decomposed function sub-terms, the variance and covariance of each response function can be represented using the partial variances of all the decomposed function sub-terms on the corresponding summatory functions, respectively. The total fluctuation of MIMOS is calculated by the sum of the variances and covariances on all the response functions. Further, the fluctuation is represented as the sum of the total partial variances for all the [Formula: see text]-order function sub-terms, and the total partial variance is the sum of [Formula: see text] partial variances for the corresponding [Formula: see text]-order function sub-terms. Then, the function sensitivity index (FSI) [Formula: see text] for s-order function sub-terms is defined by the ratio of the total partial variance and total fluctuation, which includes first-order, second-order, and high-order FSI. The variable sensitivity index [Formula: see text] of variable [Formula: see text] is calculated by the sum of all the FSIs including the contribution of variable [Formula: see text]. Finally, numerical example and engineering application are employed to demonstrate the accuracy and practicality of the presented global sensitivity analysis method for MIMOS.

How weather affects the decomposition of total factor productivity in U.S. agriculture

AbstractThis study illustrates and quantifies how overlooking the impact of weather shocks can affect the measurement and decomposition of agricultural total factor productivity (TFP) change. The underlying technology is represented by a flexible input distance function with quasi‐fixed inputs estimated with Bayesian methods. Using agricultural production and weather data for 16 states in the Pacific Region, Central Region, and Southern Plains of the United States, we estimate TFP change as the direct sum of multiple components, including a net weather effect. To assess the role of weather, we conduct a comparative analysis based on two distinct sets of input and output variables. A traditional set of variables that ignore weather variations, and a new set of “weather‐filtered” variables that represent input and output levels that would have been chosen under average weather conditions. From this comparative analysis, we derive biases in the decomposition of TFP growth from the omission of weather shocks. We find that weather shocks accelerated productivity growth in 12 out of 16 states by the equivalent of 11.4% of their group‐average TFP growth, but slowed down productivity by the equivalent of 6.5% of the group‐average TFP growth in the other four states (located in the Northern‐most part of the country). We also find substantial biases in the estimated contribution of technical change, scale effects, technical efficiency change, and output allocation effects to TFP growth (varying in magnitude and direction across regions) when weather effects are excluded from the model. This is the first study to present estimates of those biases based on a counterfactual analysis. One major implication from our study is that the official USDA's measures of TFP change would appear to overestimate the rate of productivity growth in U.S. agriculture stemming from technical change, market forces, agricultural policies, and other nonweather drivers.

Energy Efficiency in OECD Countries: A DEA Approach

This paper deals with energy efficiency examined through an integrated model that links energy with environment, technology, and urbanisation as related areas. Our main goal is to discover how efficiently developed countries use primary energy and electricity (secondary energy). We additionally want to find out how the inclusion of environmental care and renewable energy capacity affects efficiency. For that purpose, we set up an output-oriented BCC data envelopment analysis that employs a set of input variables with non-negative values to calculate the efficiency scores on minimising energy use and losses as well as environmental emissions for a sample of 30 OECD member states during the period from 2001 to 2018. We develop a couple of baseline models in which we find that countries have mean inefficiency margins of 16.1% for primary energy and from 10.8 to 13.5% for electricity. The results from the extended models show that taking care about environment does not affect efficiency in general, while the reliance on energy produced from renewable sources does slightly reduce it.

Multi-target regression via self-parameterized Lasso and refactored target space

Multi-target regression (MTR) aims at simultaneously predicting multiple continuous target variables based on the same set of input variables. It has been used to solve some challenging problems. A self-parameterized Lasso for MTR is proposed in this paper, which is applied to refactored target space via linear combinations of existing targets. Our approach can simultaneously model intrinsic inter-target correlations and input-target correlations, which makes full use of the information contained in the data. Meanwhile, this information helps automatically generate the parameters needed in the model. Compared with the common method, which requires a manual setting of parameters and is expensive to optimize these parameters, our method can save a lot of time while no reduction in performance. Besides, our method can be used not only for MTR tasks but also for multi-classification tasks. The experimental results show that our method performs well in different tasks and has a wide range of applications.

A First Approach to Aerosol Classification Using Space-Borne Measurement Data: Machine Learning-Based Algorithm and Evaluation

A new method was developed for classifying aerosol types involving a machine-learning approach to the use of satellite data. An Aerosol Robotic NETwork (AERONET)-based aerosol-type dataset was used as a target variable in a random forest (RF) model. The contributions of satellite input variables to the RF-based model were quantified to determine an optimal set of input variables. The new method, based on inputs of satellite variables, allows the classification of seven aerosol types: pure dust, dust-dominant mixed, pollution-dominant mixed aerosols, and pollution aerosols (strongly, moderately, weakly, and non-absorbing). The performance of the model was statistically evaluated using AERONET data excluded from the model training dataset. Model accuracy for classifying the seven aerosol types was 59%, improving to 72% for four types (pure dust, dust-dominant mixed, strongly absorbing, and non-absorbing). The performance of the model was evaluated against an earlier aerosol classification method based on the wavelength dependence of single-scattering albedo (SSA) and fine-mode-fraction values from AERONET. Typical wavelength dependences of SSA for individual aerosol types are consistent with those obtained for aerosol types by the new method. This study demonstrates that an RF-based model is capable of satellite aerosol classification with sensitivity to the contribution of non-spherical particles.

Feature distribution-based label correlation in multi-label classification

In multi-label classification, multiple label variables in output space are equally important and can be predicted according to a common set of input variables. To improve the accuracy and efficiency of multi-label learner, measuring and utilizing label correlation is the core breakthrough. Extensive research on label correlation focuses on the co-occurrence or mutual exclusion frequency of label values in output space. In this paper, to handle the multi-label learning tasks, a novel method, named FL-MLC, is proposed by considering the influence of feature-label dependencies on inter-label correlations. In order to describe the intrinsic relationship between feature variable and label variable, the discriminant weight of any feature to label is first defined. Therefore, the concept of feature distribution for inputs on label is proposed to reflect the discriminant weights of features to the label. The corresponding calculation process is also designed based on multiple kernel learning and kernel alignment. Furthermore, the feature distributions on different labels are integrated into the feature distribution-based label correlation by using two different aggregation strategies. Obviously, arbitrary label variables with highly similar feature distributions have strong relevance. Thus, the feature distribution-based label correlation is applied to adjust the distance between the parameters for different labels in the predictive learner of FL-MLC method. Finally, the experimental results on twelve real-world datasets demonstrate that our methods achieves good effectiveness and versatility for multi-label classification.

ANALISISTINGKATKEPUASANKONSUMEN PADA RESTORAN CEPATSAJI MENGGUNAKAN FUZZY MAMDANI

The development of technology is the root of the civilization of society in carrying out their daily activities. In its application, technology can make it easy to access information that helps people to find out certain information, one of which is the level of consumer satisfaction with fast food restaurants.Fast food restaurants have become an important factor in people's daily activities. To fulfill its role in people's lives, fast food restaurants serve food and services for their consumers. Fast food restaurants with decent service, as well as good food prices and quality will certainly result in a high level of satisfaction from consumers with these fast food restaurants.The Fuzzy Mamdani method is one part of the Fuzzy Inference System which is useful for drawing conclusions or the best decisions in uncertain problems. In its application, the criteria for fast food restaurants become variables to determine the level of consumer satisfaction with these fast food restaurants. The Fuzzy Mamdani method forms a fuzzy set of input variables, then implements the implication function, then composes the rules, then defuzzy to get the level of consumer satisfaction with fast food restaurants. In determining the level of customer satisfaction, Fuzzy Mamdani obtained an accuracy rate of 100%.

СИНТЕЗ НЕЧІТКОГО ДВУЗВ’ЯЗНОГО РЕГУЛЯТОРА ДЛЯ ЧАСТОТНИХ ЕЛЕКТРОПРИВОДІВ ЗЕРНОМЕТАЛЬНОЇ МАШИНИ З ФУНКЦІЄЮ ФОКУСУВАННЯ ПОТОКУ ЗЕРНА

Purpose. A control system for grain overloading during post-harvest processing with grain throwers has been proposed, the use of which will reduce damage and grain loss. An automated electromechanical system is presented that can be installed on agricultural machinery without additional modernization of the working bodies. Methodology. As a result of the analysis of control systems, a system with elements of fuzzy logic was selected, which will clearly define the necessary control actions and take into account additional parameters that can affect the overload process. A functional diagram of a microprocessor control system for an electric drive using a fuzzy system is proposed. The result of the system operation will be the definition of the control task for the frequency converters of the drive motors of the grain thrower mechanisms. Originality. Based on the simulation of grain flight trajectories, the dependences of the flight range on the conveyor speed and additional blowing were formed, which were used to determine the settings of the fuzzy controller. Results. Fuzzy system settings are performed: a set of input and output variables is defined; the number and location of terms are selected; a set of production rules for the system is formulated. As a result of experimental modeling, graphs of the formation of mastering influences by a fuzzy controller under the condition of the appearance and disappearance of the headwind for different given distances of movement were obtained. Practical value. Practical application of the offered system will allow to reduce material losses from injury of the overloaded grain and to increase efficiency of work of the grain thrower. Figures 8, references 21.

Прогнозування ранньої діагностики гострого пошкодження нирок у недоношених дітей з гемодинамічно значущою відкритою артеріальною протокою

The development of acute kidney injury (AKI) in preterm infants with hemodynamically significant patent ductus arteriosus (HSPDA) is an additional burden on homeostatic mechanisms, leading to loss of fluid, electrolyte balance, and acid-base disturbance and increasing the risk of mortality by 50%. Therefore, early detection of AKI in preterm infants with HSPDA is extremely important in terms of improving treatment outcomes. Purpose — to create, evaluate and further analyze the binary logistic regression model of AKI on the background of HSPDA in premature infants. Materials and methods. The group of study participants consisted of 40 premature babies with HSPDA, who were admitted for treatment on the first day of life to the Department of Anesthesiology and Neonatal Intensive Care at MI «Dnepropetrovsk Regional Children's Clinical Hospital» Dnepropetrovsk Regional Council». On the third to fifth day of life, 23 (57.5%) patients were diagnosed with AKI. Clinical and laboratory examination included obstetric history, gestational age, weight, physical examination, clinical analysis of blood and urine, arterial blood oxygen saturation, biochemical methods — examination of urea, serum and urine creatinine, serum and urine sodium, serum potassium. The concentration index of creatinine, fractional excretion of sodium, glomerular filtration rate (GFR) according to the Schwartz formula were calculated. Instrumental methods of examination included echocardiography with Doppler, ultrasound Doppler of renal vessels, renal spectroscopy in the near infrared region. In order to preliminarily determine the diagnostic potential of some clinical'anamnestic and laboratory data, the parameters of the sample with AKI and the sample without this pathology were compared: in the case of interval scale the Mann–Whitney U-test was used, in the case of categorical scale — χ2-test or Fisher's exact test. Spearman's rank correlation was used to form the optimal set of input variables for regression modeling. The method of binary logistic regression was used to develop a diagnostic model of AKI development on the background of HSPDA in premature infants. Results. At the stage of exploratory data analysis (several dozen parameters of clinical and biochemical analysis of blood and urine, renal hemodynamics, renal oxygenation and therapeutic measures on the first day), as well as clinical and anamnestic data, it was found that AKI has a significant relationship with 14 interval ( maximum blood flow velocity in the interlobar renal artery, minimum blood flow velocity in the interlobar renal artery, resistance index in the interlobar renal artery, maximum blood flow velocity in the main renal artery, diameter of the open arterial duct, renal oxygenation, fractional renal tissue extraction of oxygen, serum creatinine, GFR, creatinine concentration index, urinary sodium, fractional sodium excretion, urine protein, diastolic blood pressure) and 9 nominal values (the size of the patent ductus arteriosus on the first day of more than 2 mm, ibuprofen therapy at a dose of 20 mg/kg on the first day, ibuprofen therapy on the first day of life, furosemide treatment, history of renal disease in the mother, chronic foci of infection in the mother, hypertension of pregnancy, threat of abortion, necrotizing enterocolitis in the patient on the first day of life). Conclusions. The most significant predictors of AKI development in premature infants with HSPDA are the parameter of maximum blood flow velocity in the interlobar renal artery, HSPDA diameter greater than 2 mm and serum creatinine level on the first day of life. The sensitivity of the AKI logistic regression model, in which HSPDA diameter and serum creatinine level are used as explanatory variables, is 91%, specificity — 88%, overall accuracy — 90%. Replacement of serum creatinine in the logit function for the maximum blood flow velocity in the interlobar renal artery allows to increase the sensitivity of the model up to 96%, and the overall accuracy up to 93%. The study was conducted in accordance with the principles of the Helsinki Declaration. The research protocol was approved by the Local Ethics Committee of the institution mentioned in the work. Informed consent of parents of children was obtained for the research. The authors were declare no conflict of interest. Key words: hemodynamically significant patent ductus arteriosus, premature infants, acute kidney injury, prediction of early diagnosis.

Lifting the numbers game: identifying key input variables and a best‐performing model to detect financial statement fraud

AbstractThis study enables practitioners and researchers to make an informed choice for a financial statement fraud detection model, rather than defaulting to popular, yet dated, models. Using a specifically devised performance criterion, our newly configured ensemble outperforms 31 others in the most comprehensive comparison to date spanning parametric, non‐parametric, big data and ensemble techniques. We use a large set of input variables and holdout data relative to prior studies. We find empirical support for financial and non‐financial variables covering the three Fraud Triangle factors. New findings include fraud risk being reduced with more debt, likely from increased monitoring by creditors.

Delineation of vulnerable areas to water erosion in a mountain region using SDR-InVEST model: A case study of the Ourika watershed, Morocco

The Ourika watershed is characterized by higher than average flood flows, a rugged topography, a sparse vegetation cover and a friable substrate that makes it vulnerable to soil erosion. Soil is an important non-renewable asset capital, providing several ecosystem services that sustain life through physical and biological regulation processes. The loss, or otherwise, redistribution of biota by soil erosion in the Ourika watershed has received little attention and thus constitutes a key knowledge gap that needs to be addressed. This study quantifies the level of erosion and maps its spatial distribution in the watershed using the Sediment Delivery Ratio (SDR) of the Integrated Valuation of Ecosystem Services and Trade-offs model (InVEST 3.6.0). The SDR maps the overland sediment generation and delivery to the stream at the watershed level using rainfall, soil properties, topography, cover management and cropping practices as predefined set of input variables. Recommended internal model calibration was used and results were compared to similar studies carried out in different parts of Morocco for validation. The results reveal that 93% of the watershed is subject to a strong rainfall aggressiveness greater than 50 MJ mm ha–1 h–1 yr–1 under an average rainfall intensity of 541 mm/year, rainfall capacity to initiate the detachment and transport of soil particles by runoff, and only 11.5 % of the watershed area is protected with vegetative cover. We find that overall, the Ourika watershed is losing its soil to erosion at an alarming average rate of 258.48 ton.ha–1.yr–1, a rate well above the tolerable threshold of 7 ton.ha–1.yr–1. The spatial distribution of this loss shows areas that need to be urgently remedied. The primary factors for soil erosion in the Ourika watershed appear to be related to the aggressive nature of local rainfall and the inherent susceptibility of soils, which can be costly to this cash-crop region. Because rainfall intensity, soil properties, and topography are intrinsic characteristics of the watershed, we suggest that seasonally adapted cropping rotations that maintains conservative practices with a high cover management may reduce soil erosion in the Ourika watershed.

EVALUATION OF RANDOM FOREST–BASED ANALYSIS FOR THE GYPSUM DISTRIBUTION IN THE ATACAMA DESERT

Abstract. Gypsum-rich material covers the hillslopes above ∼ 1000 m of the Atacama and forms the particular landscape. In this contribution, we evaluate random forest-based analysis in order to predict the gypsum distribution in a specific area of ∼ 3000 km2, located in the hyperarid core of the Atacama. Therefore, three different sets of input variables were chosen. These variables reflect the different factors forming soil properties, according to digital soil mapping. The variables are derived from indices based on imagery of the ASTER and Landsat-8 satellite, geomorphometric parameters based on the Tandem-X World DEM™, as well as selected climate variables and geologic units. These three different models were used to evaluate the Ca-content derived from soil surface samples, reflecting gypsum content. All three different models derived high values of explained variation (r2 &gt; 0.886), the RMSE is ∼ 4500 mg∙kg−1 and the NRMSE is ∼ 6%. Overall, this approach shows promising results in order to derive a gypsum content prediction for the whole Atacama. However, further investigation on the independent variables need to be conducted. In this case, the ferric oxides index (representing magnetite content), slope and a temperature gradient are the most important factors for predicting gypsum content.

External Validation of Surgical Risk Preoperative Assessment System in Pulmonary Resection

Accurate preoperative risk assessment is necessary for informed decision making for patients and surgeons. Several preoperative risk calculators are available but few have been examined in the general thoracic surgical patient population. The Surgical Risk Preoperative Assessment System (SURPAS), a risk-assessment tool applicable to a wide spectrum of surgical procedures, was developed to predict the risks of common adverse postoperative outcomes using a parsimonious set of preoperative input variables. We sought to externally validate the performance of SURPAS for postoperative complications in patients undergoing pulmonary resection. Between January 2016 and December 2018, 2514 patients underwent pulmonary resection at our center. Using data from our institution's prospectively maintained database, we calculated the predicted risks of 12 categories of postoperative outcomes using the latest version of SURPAS. Performance of SURPAS against observed patient outcomes was assessed by discrimination (concordance index) and calibration (calibration curves). The discrimination ability of SURPAS was moderate across all outcomes (concordance indices, 0.640 to 0.788). Calibration curves indicated good calibration for all outcomes except infectious and cardiac complications, discharge to a location other than home, and mortality (all overestimated by SURPAS). SURPAS demonstrates outcomes for pulmonary resections with reasonable predictive ability. Discretion should be applied when assessing risk for postoperative infectious and cardiac complications, discharge to a location other than home, and mortality. Although the parsimonious nature of SURPAS is one of its strengths, its performance might be improved by including additional factors known to influence outcomes after pulmonary resection, such as sex and pulmonary function.