Biomathematical Model Research Articles

286 Pilot Sleep During Brazil-to-China COVID-19 Humanitarian Mission Flights Compared to Biomathematical Predictions of Sleep

Introductionn response to the COVID-19 pandemic, Azul Airlines organized and conducted five separate humanitarian missions to China between May and July, 2020. Each mission consisted of 4 flight legs between 11-15 hours long crewed by a team of 8 pilots. Each pilot was given a 9-hour sleep opportunity during the flight period. Prior to conducting the missions, a sleep-prediction algorithm (AutoSleep) within the Sleep, Activity, Fatigue, and Task Effectiveness (SAFTE) model Fatigue Avoidance Scheduling Tool (FAST) was used to predict in-flight time in bed (TIB) and total sleep time (TST). During missions, pilots wore a wrist actigraph and completed a sleep diary. These analyses compare the accuracy of SAFTE-FAST AutoSleep predictions against pilots’ sleep diary and actigraphy from Azul’s COVID-19 humanitarian missions.MethodsPilots wore a sleep-tracking actigraphy device (Zulu Watch, Institutes for Behavior Resources), and reported the TIB and sleep quality of their in-flight rest periods using a sleep diary. Diary TST was estimated from TIB and sleep quality. AutoSleep, diary, and actigraphy measures were compared using paired samples t-tests. Agreement was compared using intraclass correlation coefficients (ICC).ResultsTwenty (n=20) pilots flying across 5 humanitarian missions provided sleep diary and actigraphy data. AutoSleep predictions of TIB (235±20 minutes) and TST (193±16 minutes) were significantly lower than diary (TIB: 330±123, t=6.80, p≤0.001; TST: 262±108, t=5.60, p≤0.001) and comparable to actigraphy (TIB: 246±127, t=0.78, p=0.43; TST: 212±113, t=1.59, p=0.12). ICC values were >0.90, indicating excellent agreement, for TIB (0.94) and TST (0.91).ConclusionBiomathematical predictions of in-flight sleep during unprecedented humanitarian missions were in agreement with actual sleep patterns during flights. These findings indicate that biomathematical models may retain accuracy even under extreme circumstances like the COVID-19 pandemic. Pilots may overestimate the amount of sleep that they receive during extreme flights-duty periods, which could constitute a fatigue risk.Support (if any)NA

137 Recovery Dynamics in a Biomathematical Model of Fatigue

Abstract Introduction In commercial aviation and other operational settings where biomathematical models of fatigue are used for fatigue risk management, accurate prediction of recovery during rest periods following duty periods with sleep loss and/or circadian misalignment is critical. The recuperative potential of recovery sleep is influenced by a variety of factors, including long-term, allostatic effects of prior sleep/wake history. For example, recovery tends to be slower after sustained sleep restriction versus acute total sleep deprivation. Capturing such dynamics has proven to be challenging. Methods Here we focus on the dynamic biomathematical model of McCauley et al. (2013). In addition to a circadian process, this model features differential equations for sleep/wake regulation including a short-term sleep homeostatic process capturing change in the order of hours/days and a long-term allostatic process capturing change in the order of days/weeks. The allostatic process modulates the dynamics of the homeostatic process by shifting its equilibrium setpoint, which addresses recently observed phenomena such as reduced vulnerability to sleep loss after banking sleep. It also differentiates the build-up and recovery rates of fatigue under conditions of chronic sleep restriction versus acute total sleep deprivation; nonetheless, it does not accurately predict the disproportionately rapid recovery seen after total sleep deprivation. To improve the model, we hypothesized that the homeostatic process may also modulate the allostatic process, with the magnitude of this effect scaling as a function of time awake. Results To test our hypothesis, we added a parameter to the model to capture modulation by the homeostatic process of the allostatic process build-up during wakefulness and dissipation during sleep. Parameter estimation using previously published laboratory datasets of fatigue showed this parameter as significantly different from zero (p<0.05) and yielding a 10%–20% improvement in goodness-of-fit for recovery without adversely affecting goodness-of-fit for pre-recovery days. Conclusion Inclusion of a modulation effect of the allostatic process by the homeostatic process improved prediction accuracy in a variety of sleep loss and circadian misalignment scenarios. In addition to operational relevance for duty/rest scheduling, this finding has implications for understanding mechanisms underlying the homeostatic and allostatic processes of sleep/wake regulation. Support (if any) Federal Express Corporation

Dynamical Strategy to Control the Accuracy of the Nonlinear Bio-Mathematical Model of Malaria Infection

This study focuses on solving the nonlinear bio-mathematical model of malaria infection. For this aim, the HATM is applied since it performs better than other methods. The convergence theorem is proven to show the capabilities of this method. Instead of applying the FPA, the CESTAC method and the CADNA library are used, which are based on the DSA. Applying this method, we will be able to control the accuracy of the results obtained from the HATM. Also the optimal results and the numerical instabilities of the HATM can be obtained. In the CESTAC method, instead of applying the traditional absolute error to show the accuracy, we use a novel condition and the CESTAC main theorem allows us to do that. Plotting several ℏ-curves the regions of convergence are demonstrated. The numerical approximations are obtained based on both arithmetics.

Fatigue risk management based on self-reported fatigue: Expanding a biomathematical model of fatigue-related performance deficits to also predict subjective sleepiness

Biomathematical models of fatigue can be used to predict neurobehavioral deficits during sleep/wake or work/rest schedules. Current models make predictions for objective performance deficits and/or subjective sleepiness, but known differences in the temporal dynamics of objective versus subjective outcomes have not been addressed. We expanded a biomathematical model of fatigue previously developed to predict objective performance deficits as measured on the Psychomotor Vigilance Test (PVT) to also predict subjective sleepiness as self-reported on the Karolinska Sleepiness Scale (KSS). Four model parameters were re-estimated to capture the distinct dynamics of the KSS and account for the scale difference between KSS and PVT. Two separate ensembles of datasets – drawn from laboratory studies of sleep deprivation, sleep restriction, simulated night work, napping, and recovery sleep – were used for calibration and subsequent validation of the model for subjective sleepiness. The expanded model was found to exhibit high prediction accuracy for subjective sleepiness, while retaining high prediction accuracy for objective performance deficits. Application of the validated model to an example scenario based on cargo aviation operations revealed divergence between predictions for objective and subjective outcomes, with subjective sleepiness substantially underestimating accumulating objective impairment, which has important real-world implications. In safety-sensitive operations such as commercial aviation, where self-ratings of sleepiness are used as part of fatigue risk management, the systematic differences in the temporal dynamics of objective versus subjective measures of functional impairment point to a potentially significant risk evaluation sensitivity gap. The expanded biomathematical model of fatigue presented here provides a useful quantitative tool to bridge this previously unrecognized gap.

Diverse novel computational wave solutions of the time fractional Kolmogorov—Petrovskii - Piskunov and the (2 + 1)-dimensional Zoomeron equations

The numerical wave solutions of two fractional biomathematical and statistical physics models (the Kolmogorov—Petrovskii - Piskunov (KPP) equation and the (2 + 1)-dimensional Zoomeron (Z) equation) are investigated in this manuscript. Many novel analytical solutions in different mathematical formulations such as trigonometric, hyperbolic, exponential, and so on can be constructed using the generalized Riccati—expansion analytical scheme and the Caputo—Fabrizio fractional derivative. The fractional nonlinear evolution equation is converted into an ordinary differential equation with an integer order using this fractional operator. The obtained solution is used to describe the transmission of a preferred allele and the nonlinear interaction of moving waves, and the relative wave mode’s amplitude dynamic. To illustrate the fractional examined models, several drawings are explained in two dimensions and density plots.

Radiomics and Magnetic Resonance Imaging of Rectal Cancer: From Engineering to Clinical Practice.

While cross-sectional imaging has seen continuous progress and plays an undiscussed pivotal role in the diagnostic management and treatment planning of patients with rectal cancer, a largely unmet need remains for improved staging accuracy, assessment of treatment response and prediction of individual patient outcome. Moreover, the increasing availability of target therapies has called for developing reliable diagnostic tools for identifying potential responders and optimizing overall treatment strategy on a personalized basis. Radiomics has emerged as a promising, still fully evolving research topic, which could harness the power of modern computer technology to generate quantitative information from imaging datasets based on advanced data-driven biomathematical models, potentially providing an added value to conventional imaging for improved patient management. The present study aimed to illustrate the contribution that current radiomics methods applied to magnetic resonance imaging can offer to managing patients with rectal cancer.

Understanding fatigue in a naval submarine: Applying biomathematical models and workload measurement in an intensive longitudinal design

Fatigue is a critically important aspect of crew endurance in submarine operations, with continuously high fatigue being associated with increased risk of human error and long-term negative health ramifications. Submarines pose several unique challenges to fatigue mitigation, including requirements for continuous manning for long durations, a lack of access to critical environmental zeitgebers (stimuli pertinent to circadian physiology; e.g., natural sunlight), and work, rest and sleep occurring within an encapsulated environment. In this paper, we examine the factors that underlie fatigue in such a context with the aim of evaluating the predictive utility of a biomathematical model (BMM) of fatigue. Three experience sampling studies were conducted with submarine crews using a participant-led measurement protocol that included assessments of subjective sleepiness, workload (NASA-Task Load Index [TLX] and a bespoke underload-overload scale), and sleep. As expected, results indicated that predicting KSS with a BMM approach outperformed more conventional linear modelling approaches (e.g., time-of-day, sleep duration, time awake). Both the homeostatic and circadian components of the BMM were significantly associated with KSS and used as controls in the workload models. We found increased NASA-TLX workload was significantly associated with increased average KSS ratings at the between-person level. However, counter to expectations, the two workload measures were not found to have significant linear or quadratic relationship with fatigue at the within-person level. An important outcome of the research is that applied fatigue researchers should be extremely cautious applying conventional linear predictors when predicting fatigue. Practical implications for the submarine and related extreme work context are discussed. Important avenues for continued research are outlined, including directly estimating BMM parameters.

The biothermal analysis of a human eye subjected to exponentially decaying laser radiation under the dual phase-lag heat conduction law

In this paper, a biomathematical model of the human eye subjected to an exponentially decaying laser concerning the change in blood perfusion, porosity, evaporation rate, and ambient temperatures, has been constructed based on dual phase-lag (DPL) heat conduction law. The human eye has been divided into six layers. Appropriate boundary and interface continuity conditions have been considered. A separable function has been assumed, and twelve equations have been formulated in a matrix form. The solutions have been calculated by using MAPLE. The results have been shown in figures with different cases. The absolute temperature distribution based on various values of the power density of laser irradiation and relaxation times parameters have been discussed first. The effect of the porosity, evaporation rate, time, and ambient temperatures have also been discussed. The power density of laser irradiation, porosity, evaporation rate, time, and ambient temperatures have significant effects on the temperature passing through the human eye layers.

Modeling hepatocellular carcinoma cells dynamics by serolo-gical and imaging biomarkers in patients with response to sorafenib and/or regorafenib

Introduction: In advanced HCC the overall benefits of multi-kinase inhibitors are limited, but some patients show partial response (PR) and a few achieve complete response (CR). Bio-mathematical modeling of in-vivo cancer cell dynamics by radiomics combining digital imaging and serological biomarkers would provide a better understanding of PR/CR.

In silico model reveals the key role of GABA in KCNT1-epilepsy in infancy with migrating focal seizures.

This study was undertaken to investigate how gain of function (GOF) of slack channel due to a KCNT1 pathogenic variant induces abnormal neuronal cortical network activity and generates specific electroencephalographic (EEG) patterns of epilepsy in infancy with migrating focal seizures. We used detailed microscopic computational models of neurons to explore the impact of GOF of slack channel (explicitly coded) on each subtype of neurons and on a cortical micronetwork. Then, we adapted a thalamocortical macroscopic model considering results obtained in detailed models and immature properties related to epileptic brain in infancy. Finally, we compared simulated EEGs resulting from the macroscopic model with interictal and ictal patterns of affected individuals using our previously reported EEG markers. The pathogenic variants of KCNT1 strongly decreased the firing rate properties of γ-aminobutyric acidergic (GABAergic) interneurons and, to a lesser extent, those of pyramidal cells. This change led to hyperexcitability with increased synchronization in a cortical micronetwork. At the macroscopic scale, introducing slack GOF effect resulted in epilepsy of infancy with migrating focal seizures (EIMFS) EEG interictal patterns. Increased excitation-to-inhibition ratio triggered seizure, but we had to add dynamic depolarizing GABA between somatostatin-positive interneurons and pyramidal cells to obtain migrating seizure. The simulated migrating seizures were close to EIMFS seizures, with similar values regarding the delay between the different ictal activities (one of the specific EEG markers of migrating focal seizures due to KCNT1 pathogenic variants). This study illustrates the interest of biomathematical models to explore pathophysiological mechanisms bridging the gap between the functional effect of gene pathogenic variants and specific EEG phenotype. Such models can be complementary to in vitro cellular and animal models. This multiscale approach provides an in silico framework that can be further used to identify candidate innovative therapies.

Individual prediction of thrombocytopenia at next chemotherapy cycle: Evaluation of dynamic model performances

Thrombocytopenia is a common major side-effect of cytotoxic cancer therapies. A clinically relevant problem is to predict an individual's thrombotoxicity in the next planned chemotherapy cycle in order to decide on treatment adaptation. To support this task, 2 dynamic mathematical models of thrombopoiesis under chemotherapy were proposed, a simple semimechanistic model and a comprehensive mechanistic model. In this study, we assess the performance of these models with respect to existing thrombocytopenia grading schemes. We consider close-meshed individual time series data of 135 non-Hodgkin's lymphoma patients treated with 6 cycles of CHOP/CHOEP chemotherapies. Individual parameter estimates were derived on the basis of these data considering a varying number of cycles per patient. Parsimony assumptions were applied to optimize parameter identifiability. Models' predictability are assessed by determining deviations of predicted and observed degrees of thrombocytopenia in the next cycles. The mechanistic model results in better agreement of model prediction and individual time series data. Prediction accuracy of future cycle toxicities by the mechanistic model is higher even if the semimechanistic model is provided with data of more cycles for calibration. We successfully established a quantitative and clinically relevant method for assessing prediction performances of biomathematical models of thrombopoiesis under chemotherapy. We showed that the more comprehensive mechanistic model outperforms the semimechanistic model. We aim at implementing the mechanistic model into clinical practice to assess its utility in real life clinical decision-making.

Addressing fatigue in medical residents with biomathematical fatigue modeling.

Fatigue in resident physicians has been identified as a factor that contributes to burnout and a decline in overall wellbeing. Fatigue risk exists because of poor sleep habits and demanding work schedules that have only increased due to the COVID‐19 pandemic. At this time, it is important not to lose sight of how fatigue can impact residents and how fatigue risk can be mitigated. While fatigue mitigation is currently addressed by duty hour restrictions and education about fatigue, Fatigue Risk Management Systems (FRMSs) offer a more comprehensive strategy for addressing these issues. An important component of FRMS in other shiftwork industries, such as aviation and trucking, is the use of biomathematical models to prospectively identify fatigue risk in work schedules. Such an approach incorporates decades of knowledge of sleep and circadian rhythm research into shift schedules, taking into account not just duty hour restrictions but the temporal placement of work schedules. Recent research has shown that biomathematical models of fatigue can be adapted to a resident physician population and can help address fatigue risk. Such models do not require subject matter experts and can be applied in graduate medical education program shift scheduling. It is important for graduate medical education program providers to consider these alternative methods of fatigue mitigation. These tools can help reduce fatigue risk and may improve wellness as they allow for a more precise fatigue management strategy without reducing overall work hours.

The Sleep of Shift Workers in a Remote Mining Operation: Methodology for a Randomized Control Trial to Determine Evidence-Based Interventions.

Shiftwork may adversely impact an individual’s sleep-wake patterns and result in sleep loss (<6 h. following night shift), due to the circadian misalignment and the design of rosters and shifts. Within a mining operation, this sleep loss may have significant consequences due to fatigue, including an increased risk of accidents and chronic health conditions. This study aims to (i) determine the efficacy of an intervention that comprises a sleep education program and biofeedback through a smartphone app on sleep quality, quantity, and alertness (ii) determine the prevalence of risk for a potential sleep disorder, and (iii) quantify and describe the sleep habits and behaviors of shift workers in a remote mining operation. This study consists of a randomized controlled trial whereby eighty-eight shift workers within a remote mining operation are randomized to a control group or one of three different treatment groups that are: (i) a sleep education program, (ii) biofeedback on sleep through a smartphone app, or (iii) a sleep education program and biofeedback on sleep through a smartphone app. This study utilizes wrist-activity monitors, biomathematical modeling, and a survey instrument to obtain data on sleep quantity, quality, and alertness. A variety of statistical methods will determine the prevalence of risk for a potential sleep disorder and associations with body mass index, alcohol, and caffeine consumption. A generalized linear mixed model will examine the dependent sleep variables assessed at baseline and post-intervention for the control group and intervention groups, as well as within and between groups to determine changes. The findings from this study will contribute to the current understanding of sleep and alertness behaviors, and sleep problems and disorders amongst shift workers. Importantly, the results may inform fatigue policy and practice on interventions to manage fatigue risk within the mining industry. This study protocol may have a broader application in other shiftwork industries, including oil and gas, aviation, rail, and healthcare.

Using a biomathematical model to assess fatigue risk and scheduling characteristics in Canadian wildland firefighters

This study examined the shift parameters that contribute to sleep loss and on-duty fatigue in British Columbia Wildfire Service (BCWS) firefighters using sleep–wake data, work–rest data and alertness and fatigue predictions from a biomathematical model (BMM) of fatigue. A total of 40 firefighters (age: 30.4 ± 11.6 years; 13 F, 26 M) volunteered over a 14-day consecutive fireline deployment, followed by a 3-day rest period, at two separate fires in British Columbia (during the 2015 fire season). Sleep–wake data were obtained using a wrist-worn accelerometer and self-reported sleep logs. Shift start and end times were provided by the BCWS at the completion of the study. Sleep and shift data were manually entered into a validated BMM (Circadian Alertness Simulator) to generate fatigue scores and shift work patterns. Shift duration was the major contributor to fatigue, as 46% (n = 274) of shifts were ≥14 h in length and the average shift length was 13.0 ± 0.62 h. However, none of the firefighters had a high-risk fatigue score (&gt;60). The findings from this study indicated that using a BMM of fatigue can provide important insights into shift-work parameters that contribute to workplace fatigue and sleep loss in wildland firefighters.

Editorial: Applications of Fuzzy Systems in Data Science and Big Data

The papers in this special section focus on applications of fuzzy systems in data science and Big Data. In the era of Big Data, intelligent as well as fuzzy tools have become very important to understanding our changing Internet-of-Things-driven data-centric world. Extracting “intelligence” from massive amounts of data has allowed us to support decision making processes in many fields, ranging from common fields like medicine and engineering to more lucrative industries such as vehicular technology and environmental stressors. In line with the shift in many industries to analyzing big data, has added in the fuzzy perspective to allow new ways of reasoning. Examples include interpretability of computing schemes, which have become more and more complex. Yet, successful applications of biomathematical modeling in a fuzzy environment have shown a good alternative to mere common black-box tools. In the call for papers of this special issue, we had devoted our interest in research pertaining to the current state-of-the-art research in the application of fuzzy systems regarding data science and big data analytics. We actively solicited recent results mainly concerned with recent advances and challenges in the theory and applications of fuzzy systems in the fields of data sciences and big data environments.

A kinetic model of continuous radiation damage to populations of cells: comparison to the LQ model and application to molecular radiotherapy

The linear-quadratic (LQ) model to describe the survival of irradiated cells may be the most frequently used biomathematical model in radiotherapy. There has been an intense debate on the mechanistic origin of the LQ model. An interesting approach is that of obtaining LQ-like behavior from kinetic models, systems of differential equations that model the induction and repair of damage. Development of such kinetic models is particularly interesting for application to continuous dose rate therapies, such as molecular radiotherapy or brachytherapy. In this work, we present a simple kinetic model that describes the kinetics of populations of tumor cells, rather than lethal/sub-lethal lesions, which may be especially useful for application to continuous dose rate therapies, as in molecular radiotherapy. The multi-compartment model consists of a set of three differential equations. The model incorporates in an easy way different cross-interacting compartments of cells forming a tumor, and may be of especial interest for studying dynamics of treated tumors. In the fast dose delivery limit, the model can be analytically solved, obtaining a simple closed-form expression. Fitting of several surviving curves with both this solution and the LQ model shows that they produce similar fits, despite being functionally different. We have also investigated the operation of the model in the continuous dose rate scenario, firstly by fitting pre-clinical data of tumor response to 131I-CLR1404 therapy, and secondly by showing how damage repair and proliferation rates can cause a treatment to achieve control or not. Kinetic models like the one presented in this work may be of special interest when modeling response to molecular radiotherapy.

A biomathematical model of immune response and barrier function in mice with pneumococcal lung infection.

Pneumonia is one of the leading causes of death worldwide. The course of the disease is often highly dynamic with unforeseen critical deterioration within hours in a relevant proportion of patients. Besides antibiotic treatment, novel adjunctive therapies are under development. Their additive value needs to be explored in preclinical and clinical studies and corresponding therapy schedules require optimization prior to introduction into clinical practice. Biomathematical modeling of the underlying disease and therapy processes might be a useful aid to support these processes. We here propose a biomathematical model of murine immune response during infection with Streptococcus pneumoniae aiming at predicting the outcome of different treatment schedules. The model consists of a number of non-linear ordinary differential equations describing the dynamics and interactions of the pulmonal pneumococcal population and relevant cells of the innate immune response, namely alveolar- and inflammatory macrophages and neutrophils. The cytokines IL-6 and IL-10 and the chemokines CCL2, CXCL1 and CXCL5 are considered as major mediators of the immune response. We also model the invasion of peripheral blood monocytes, their differentiation into macrophages and bacterial penetration through the epithelial barrier causing blood stream infections. We impose therapy effects on this system by modelling antibiotic therapy and treatment with the novel C5a-inactivator NOX-D19. All equations are derived by translating known biological mechanisms into equations and assuming appropriate response kinetics. Unknown model parameters were determined by fitting the predictions of the model to time series data derived from mice experiments with close-meshed time series of state parameters. Parameter fittings resulted in a good agreement of model and data for the experimental scenarios. The model can be used to predict the performance of alternative schedules of combined antibiotic and NOX-D19 treatment. We conclude that we established a comprehensive biomathematical model of pneumococcal lung infection, immune response and barrier function in mice allowing simulations of new treatment schedules. We aim to validate the model on the basis of further experimental data. We also plan the inclusion of further novel therapy principles and the translation of the model to the human situation in the near future.

Trends in Strategic Napping in Surgical Residents by Gender, Postgraduate Year, Work Schedule, and Clinical Rotation

To identify surgical resident and clinical rotation attributes which predict on-shift napping through objectively measured sleep patterns and work schedules over a 2-month period. In a cross-sectional study, participants provided schedules, completed the Epworth Sleepiness Scale (ESS), and wore sleep-tracking devices (Zulu watch) continuously for 8 weeks. Multiple linear regression predicted percent days with on-shift napping from resident and rotation characteristics. Greater Washington, DC area hospitals. Twenty-two (n = 22) surgical residents rotating in at least 1 of 5 different clinical rotation categories. Residents slept 6 hours within a 24-hour period (370 ± 129 minutes) with normal sleep efficiency (sleep efficiency (SE): 87.13% ± 7.55%). Resident ESS scores indicated excessive daytime sleepiness (11.64 ± 4.03). Ninety-five percent (n = 21) of residents napped on-shift. Residents napped on-shift approximately 32% of their working days and were most likely to nap when working between 23:00 and 05:00 hours. Earlier shift start times predicted less on-shift napping (B = -0.08, SE = 0.04, β = -2.40, t = -2.09, p = 0.05) while working more night shifts (B = 1.55, SE = 0.44, β = 4.12, t = 3.52, p = 0.003) and shifts over 24 hours (B = 1.45, SE = 0.55, β = 1.96, t = 2.63, p = 0.01) predicted more frequent on-shift napping. Residents are taking advantage of opportunities to nap on-shift. Working at night seems to drive on-shift napping. However, residents still exhibit insufficient sleep and daytime sleepiness which could reduce competency and represent a safety risk to themselves and/or patients. These findings will help inform intervention strategies which are tailored to surgical residents using a biomathematical model of fatigue.

Regression models for productivity prediction in cactus pear cv. Gigante

ABSTRACT The understanding of plant behavior and its reflexes on yield is essential for rural planning; thus, the biomathematical models are promising in the yield prediction of cactus pear cv. Gigante. This study aimed to adjust, through simple and multiple regression analysis, models for predicting the yield of cactus pear cv. Gigante. The study, using homogeneous treatments, was developed at the Instituto Federal Baiano, Campus of Guanambi, Bahia, Brazil. Data were collected in an area consisting of 384 basic units (plants), in which the yield, defined as a dependent variable, and the predictor variables: plant height (PH), cladode length (CL), cladode width (CW), and cladode thickness (CT), number of cladodes (NC), cladode area (CA), and total cladode area (TCA) were evaluated. Simple linear regression models, multiple regression models only with simple effects for the explanatory variables, and the multiple regression models considering the simple and quadratic effects, and all its possible interactions were adjusted. From this last model, a reduced model was obtained by discarding the less relevant effects, using the Stepwise methodology. The use of the vegetative traits, TCA, NC, CA, CL, CT, and CW, through the adoption of multiple linear regression, quadratic interaction or just the variable TCA by the use of simple linear regression, allows the yield prediction of cactus pear, with adjusted R² of 0.82, 0.76, and 0.74, respectively.

Artificial Intelligence by Artificial Neural Networks to Simulate Oat (Avena sativa L.) Grain Yield Through the Growing Cycle

Artificial neural networks simulating oat grain yield throughout the crop cycle, can represent an innovative proposal regarding management and decision making, reducing costs and maximizing profits. The objective of the study is to develop biomathematical models via artificial neural networks, capable of predicting the productivity of oat grains by meteorological variables, nitrogen management and biomass obtained throughout the development cycle, making it possible to plan more efficient and sustainable managements. In each cultivation system (soybeans/oats; maize/oats), two experiments were carried out in 2017 and 2018, one for analyzing grain yield and the other for cutting every 30 days to obtain biomass. The experiments were conducted in a randomized block design with four replications for four levels of N-fertilizer (0, 30, 60 and 120 kg ha-1), applied in the stage of the 4th expanded leaf. The use of the artificial neural network makes it possible to predict grain yield by harvesting the biomass obtained at any stage of oat development, together with the handling of the nitrogen dose and meteorological information during cultivation. Therefore, a new tool to aid the simulation of oat productivity throughout the cycle, facilitating faster decision making for more efficient and sustainable management with the crop.