Time series predictive modeling for filter maintenance in water treatment plants

doi:10.22167/2675-6528-202602860

Article

October 02, 2026

Time series predictive modeling for filter maintenance in water treatment plants

Predictive Modeling by Time Series for Filter Maintenance in Water Treatment Plants

Eduardo Antonio Ribeiro Heinisch; Gustavo Nazato Furlan

DOI: 10.22167/2675-6528-202602860

Article derived from a Course Conclusion Work (TCC), with content based on the student’s original work and adapted to the editorial format of the E&S Magazine with the support of the ResumeAI tool, an artificial intelligence solution developed by Instituto Pecege for textual synthesis and organization.

Summary

The maintenance of filters in water treatment plants (WTPs) is crucial for water quality, and anticipating turbidity peaks is fundamental to optimizing backwashes. The research proposed the application of predictive algorithms to anticipate these peaks in filtered water, providing decision-making support for filter maintenance. A robust historical database (2009 to 2025) of operational data from the WTP’s industrial management corporate system and rainfall data from INMET was used. The study compared models based on trees (Random Forest and XGBoost) and recurrent neural networks (LSTM). After preprocessing and feature engineering, which consisted of creating temporal lags and moving averages, the results demonstrated that the LSTM model showed a greater capacity for time series generalization. From a practical filter operation standpoint, by converting regression predictions into binary classification alerts, adhering to the 0.30 NTU limit, the model demonstrated a 55% preventive anticipation capacity of critical events. It was concluded that the data-driven approach proved viable and acted as a proactive tool, capable of ensuring water treatment quality and assisting operators in minimizing waste from unnecessary backwashes.

Keywords: Deep Learning; LSTM; Machine Learning; Water Treatment; Turbidity.

1. Introduction

With the advancement of technology and the growing availability of data, the field of Data Science has evolved at a rapid pace, consolidating itself as a promising solution for organizations seeking to make predictions about the future based on past data (Gujarati and Porter, 2011; Montgomery and Runger, 2016). In this scenario, the high capacity for data storage, generation, and availability, characterized by the dimensions of volume, velocity, variety, variability, and complexity, has driven Machine Learning as a tool capable of learning through the association of different data and pattern recognition (Géron, 2021; Hastie et al., 2009).

The application of this predictive context in the sanitation sector, focusing on predicting the maintenance of filters in water treatment plants (WTPs), is of utmost importance. The quality, efficiency, and frequency of filter washing in a WTP are crucial factors that directly impact the quality of water supplied to the population and operational costs (Libânio, 2010; Sarmento, 2023; Abraão, 2025). Optimizing this stage means significantly reducing the waste of treated water, ensuring the safety and efficiency of the treatment (Libânio, 2010; Batista, 2024; Maciel et al., 2024).

However, filter washing can consume a significant volume of the total production of a WTP. Inefficient washing, whether due to excessive time, inadequate frequency, or improper technique, represents a great waste of potable water and, consequently, a financial and environmental loss (Libânio, 2010; Freires, 2023; Nominato, 2024). The unpredictability of the ideal washing moment is aggravated by seasonal variations in raw water quality, especially in Brazil, where the rainfall regime directly and immediately influences surface water sources. During periods of intense rain, the transport of solid particles drastically increases turbidity, while in dry months the values tend to stabilize at low levels (Libânio, 2010).

This cyclical and high-variance behavior imposes continuous challenges on the operation of Water Treatment Plants (ETAs) (Libânio, 2010; AESBE, 2023; Instituto Trata Brasil, 2024; Mesquita, 2025). Furthermore, the management of water treatment plants often encounters data governance limitations, with the recording of turbidity measurements and the control of filter run times still relying on manual annotations and human imputations. This operational dependence makes the process vulnerable to typing errors, reading failures, and, mainly, human bias, where the decision to wash a filter may be based more on the operator’s subjective interpretation than on the actual water condition. In this context, data-driven automation emerges as a fundamental mechanism to mitigate human errors and standardize decision-making.

To mitigate the complexity imposed by these climatic, operational, and data governance variations, the transition from empirical and purely reactive methods to predictive approaches has been consolidated as a critical necessity in the sanitation sector. Recent literature shows that the integration of data-driven analytical models in WTPs not only enhances water security but also provides operational resilience against sudden turbidity peaks (Kamyab et al., 2023; Dalibard et al., 2024; He et al., 2024; Kwarko-Kyei et al., 2025). Given this latent difficulty in predicting filter run time and the need to define the optimal backwash time to avoid waste (Libânio, 2010; BRK Ambiental, 2022), the present work is justified by the application of knowledge and tools acquired in Data Science to solve a real problem. The main objective of this study was to develop and compare the empirical performance of different Machine Learning predictive models — Random Forest, XGBoost, and Long Short-Term Memory (LSTM) — to predict water turbidity and, consequently, the ideal filter maintenance window.

2. Material and Methods

This study was characterized as a quantitative research, with a methodological approach focused on predictive modeling using time series. The main objective was to develop and compare the performance of different Machine Learning algorithms to predict the turbidity of filtered water in water treatment plants (WTPs) and, consequently, identify the ideal window for filter maintenance. The research was based on the proposition that there is a dependency relationship between operational and climatic variables and the need for filter maintenance (Fávero and Belfiore, 2017).

The unit of analysis consisted of historical operational data from a WTP and rainfall data. Data collection covered the period from 2009 to 2025, totaling approximately 500,000 hourly records. The information was extracted from two main sources: the WTP’s corporate industrial management system, which provided turbidity measurements, schedules, washing time, and water consumption volume, and stations from the National Institute of Meteorology (INMET, 2026), located in the same catchment basin, which provided daily precipitation data.

The study’s development was implemented in the Python language, using consolidated libraries for data analysis and Machine Learning. Among the tools employed, Pandas and NumPy stand out for data manipulation, Scikit-Learn for preprocessing and modeling, and TensorFlow/Keras for building neural networks (Fávero and Belfiore, 2017; McKinney, 2018; Géron, 2021).

The preprocessing stage of pluviometric data involved the identification and correction of anomalies, such as recording failures or corrupted values, through the linear interpolation technique. Subsequently, the two databases, operational and meteorological, were unified using date and time as a temporal index, ensuring information synchronization.

In the feature engineering phase, temporal variables were created to capture the inertia of the hydrological system. Lag variables were included for precipitation, measuring rainfall that occurred in intervals of 1 hour, 2 hours, and up to 48 hours prior. Rolling windows were also generated for the sum of accumulated precipitation over multiple periods, such as 12, 24, 48, and 72 hours (Libânio, 2010; Kuhn and Johnson, 2019).

Additionally, to allow the algorithms to identify cyclical patterns, seasonality extraction was performed. The temporal index was broken down into independent columns for ‘Hour’ and ‘Month’. The predictive target variable, water turbidity, was temporally shifted by 6 hours (“lead time”) so that the model could make estimates with sufficient advance for operational decision-making.

Outlier treatment was performed to correct data distortions, which could arise from typing errors or reading failures. Negative turbidity readings were adjusted to the minimum physically admissible. For anomalous values exceeding the upper limit, the capping/winsorizing technique based on the Interquartile Range (IQR) method was applied, preserving the continuity of the time series (Fávero and Belfiore, 2017; McKinney, 2018).

For model validation, the dataset was chronologically split, with the first 80% allocated for training and the final 20% reserved for testing, preventing data leakage. The predictor variables were normalized using StandardScaler for tree-based models and MinMaxScaler for the LSTM network, with standardization applied exclusively to the training data (Baouab and Cherif, 2017).

Four algorithms were selected for comparison: Random Forest, XGBoost, and Long Short-Term Memory (LSTM) as predictive models, and SHAP (SHapley Additive exPlanations) for interpretability. The Random Forest was configured with 100 decision trees and a random state (random_state=42). The XGBoost used 100 sequential trees, a learning rate of 0.1, and a random state (random_state=42). The LSTM network was built with a layer of 50 neurons, ReLU activation, 20% Dropout, 24-hour lookback, Adam optimizer, and Early Stopping with 5 epochs (Géron, 2021; Goodfellow et al., 2016; Chollet, 2017).

The validation protocol was structured in two phases. In Phase 1, a continuous predictive evaluation (regression) was performed, where the models were compared using statistical metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²). In Phase 2, an operational decision evaluation (binary classification) was carried out, converting regression predictions into binary classification alerts, with a cutoff threshold of 0.30 NTU for critical events. The evaluation of this phase used the confusion matrix, focusing on the Recall metric, to minimize false negatives (Libânio, 2010; Kuhn and Johnson, 2019; Géron, 2021).

3. Results and Discussion

Exploratory data analysis (EDA) revealed crucial patterns and interrelationships between variables before applying predictive algorithms. The seasonality of turbidity in Brazilian water sources, for example, showed a strong correlation with the rainfall regime. It was observed that during months of intense rainfall, typically from November to March, turbidity rises drastically due to the transport of solid particles. In contrast, during dry months, from May to September, turbidity levels tend to stabilize at lower levels, as previously identified by Libânio (2010).

The evaluation of Pearson’s linear correlation between the variables, including temporal lags and accumulated precipitation variables, indicated that, although the direct linear correlation with final turbidity was low, the hydrological system’s inertia and input turbidity are important immediate predictors. Cross-correlation analysis was fundamental to quantitatively validate the watershed’s response time to precipitation. An ideal “lag” was identified, where accumulated rainfall reaches its maximum correlation with turbidity at the WTP, reinforcing the need to incorporate temporal windows in modeling to capture this delayed effect (Libânio, 2010; Kuhn and Johnson, 2019).

The importance of variables (Feature Importance) was extracted using the Random Forest algorithm, confirming the data relevance raised in the preprocessing. Variables related to the duration and volume of the last wash, the turbidity of the result and the filter turbidity, along with accumulated precipitation in different time windows, showed the highest importance indices. This finding corroborates previous studies, such as that of Kwarko-Kyei et al. (2025), which highlight water quality in the stage immediately before filtration as the attribute with the greatest weight in reducing predictive error.

The predictive modeling stage compared the performance of three algorithms: Random Forest, XGBoost, and Long Short-Term Memory (LSTM). The tree-based models, Random Forest and XGBoost, encountered difficulties in handling the predictability of continuous turbidity, resulting in negative determination coefficients R² of -0.313333 and -0.252568, respectively. These values indicate that these models failed to explain the variability of the time series satisfactorily, treating turbidity peaks as isolated noises rather than continuous patterns (Hewamalage et al., 2021; Géron, 2021).

In contrast, the LSTM model demonstrated superior and more stable performance, with a Mean Absolute Error (MAE) of 0.062854, a Root Mean Squared Error (RMSE) of 0.080221, and a positive R² of 0.152867. Although the R² is still modest, reflecting the complexity and stochasticity of the hydrological series, the LSTM was the only model capable of capturing temporal patterns and the directional dynamics of turbidity, successfully anticipating upward and downward movements. This generalization capability is crucial for dynamic time series, as pointed out by He et al. (2024).

The architecture of the LSTM model was configured with a layer of 50 neurons and ReLU activation, followed by a 20% Dropout layer to prevent overfitting, a common problem in time series modeling (Goodfellow et al., 2016). Training used the Adam optimizer to minimize the Mean Squared Error (MSE), and Early Stopping was implemented to halt the process if the validation loss did not improve for five consecutive epochs, ensuring the restoration of the best model weights (Chollet, 2017).

The convergence of the mean squared error (MSE) during the LSTM model training demonstrated the neural network’s stability. It was observed that both training and validation errors stabilized jointly, which proves the effectiveness of Dropout and Early Stopping techniques in preventing overfitting. This behavior is an indication that the model learned the data patterns robustly, without memorizing noise specific to the training set.

For practical application purposes in the operation of the Water Treatment Plant (WTP), the study’s main contribution was directed towards the identification of “critical events”, rather than the exact prediction of continuous turbidity. Predicting the exact turbidity value at each instant proved less relevant than the system’s ability to detect, in advance, moments of risk. Thus, the continuous regression model was adapted for a binary classification problem, aiming to generate operational alerts for filter maintenance.

The business rule established for binary classification was as follows: if the predicted turbidity exceeded the threshold of 0.30 NTU, an intervention alert (filter washing) should be issued. Predictions with a probability above 50% generated a maintenance/washing “Alert”. This approach aims to act preventively, minimizing false negatives, i.e., the failure to predict high turbidity, which is more critical for water treatment safety than false positives (Libânio, 2010; Kuhn and Johnson, 2019; Géron, 2021).

The evaluation of the binary classifier, using the confusion matrix, revealed a Global Accuracy of 77%, indicating the model’s total hit rate. The Sensitivity (Recall) metric, which measures the ability to detect real turbidity peaks (critical events), reached 55%. This value demonstrates that the model acts as a conservative barrier, capable of anticipating the event and alerting the operator most of the times when the filter presents a real risk, prioritizing the safety of treated water (Hastie et al., 2009; Fávero and Belfiore, 2017).

The model’s precision was 60%, indicating that, of the times the model issued a “Warning” of backwash, the turbidity actually rose in 60% of the cases. Although precision is not as high as accuracy, the operational priority in water treatment safety justifies the preference for a higher Recall, even if this implies a slightly higher number of false positives, i.e., preventive backwashes that could be considered unnecessary in a lower-risk scenario.

The ROC (Receiver Operating Characteristic) Curve of the LSTM classifier presented an Area Under the Curve (AUC) of 0.797. This value attests to the model’s general robustness in correctly discriminating between the states of “normal operation” and “high turbidity risk”, regardless of the probabilistic threshold chosen by the operator. Obtaining an AUC score far from the randomness line (AUC = 0.5) on a test set with over 12,000 independent samples significantly rejects the null hypothesis, conferring robust statistical significance (p-value < 0.001) to the findings (Hastie et al., 2009; Fávero and Belfiore, 2017; Géron, 2021).

The interpretability of the LSTM model was addressed through SHAP (SHapley Additive exPlanations) analysis, a technique that allows quantifying the influence of each variable on the prediction of future turbidity. Unlike the static importance of Random Forest, SHAP provided a global importance ranking for the LSTM network, highlighting `tuf_resultado`, `Hour`, `Month`, `precipitacao`, and `ultima_lavagem_volume` as the most crucial variables for accurately capturing the dynamic water oscillations (Kuhn and Johnson, 2019; Maußner et al., 2025).

SHAP analysis also allowed visualizing the directional impact of variables on turbidity prediction. Red dots in the swarm plot indicated that high values of a variable pushed the turbidity prediction upwards (increasing the risk), while blue dots indicated that low values pushed the prediction downwards. This transparency, characteristic of Explainable AI, increases confidence in the tool, as it proves that the LSTM algorithm’s predictions are based on the real physics of the filtration process, and not on “guesses” (Dalibard et al., 2024; Kamyab et al., 2023; Maußner et al., 2025).

To consolidate the practical utility of the predictive model, a Python function was developed that simulates a decision support tool for the operator. This function allows the manual insertion of a punctual turbidity reading, which is then integrated into the recent historical context of the WTP (rainfall, previous washes, and system inertia) to calculate and display the immediate probability of a critical event, recommending the appropriate action. This tool aims to mitigate human errors and standardize decision-making, elevating the plant’s technological maturity.

In summary, the results demonstrated that the application of predictive algorithms, especially the LSTM model, is viable for anticipating turbidity peaks in filtered water at treatment plants. Although continuous regression has limitations in explaining the entirety of the variability, the conversion to a binary operational alert classifier allowed the model to act as a proactive tool, with a 55% preventive anticipation capacity of critical events. This ensures the quality of water treatment and assists operators in optimizing filter maintenance, minimizing waste from unnecessary backwashes, thus responding to the study’s main objective.

4. Conclusion

This study aimed to develop and compare the performance of Machine Learning predictive models to anticipate water turbidity and optimize filter maintenance in treatment plants. It was found that the non-stationary nature of hydrological time series imposed significant challenges on the algorithms. Tree-based models, such as Random Forest and XGBoost, showed notable limitations, with negative R² coefficients of determination, indicating difficulty in capturing the variability and continuous patterns of turbidity. In contrast, the Long Short-Term Memory (LSTM) model demonstrated superior generalization capability, with a positive R² and more stable error metrics, successfully capturing the directional dynamics of turbidity. The practical application of the model was consolidated by converting its regression predictions into binary classification alerts, establishing a threshold of 0.30 NTU for critical events. This approach resulted in a sensitivity (Recall) of 55% in anticipating these events, prioritizing operational safety. SHAP analysis complemented the findings, providing transparency to the LSTM model and confirming that its predictions are based on relevant operational and environmental attributes, such as previous turbidity, hour, month, and accumulated precipitation.

The study’s main contribution lies in demonstrating the feasibility of a data-driven predictive approach as a proactive tool for water treatment plant management. By providing decision support for filter maintenance, the model assists operators in standardizing procedures, mitigating human bias, and minimizing the waste of potable water associated with unnecessary backwashes, thereby enhancing the plant’s technological maturity. However, it is acknowledged that the modest R² in the continuous regression reflects the inherent complexity and stochasticity of hydrological series. For future studies, it is suggested to optimize the hyperparameters of the LSTM architecture, include additional real-time variables such as pH and temperature, and stratify the database for developing specific models for different filter categories and typologies, aiming to further refine accuracy and reduce false alarm rates.

Bibliographic References

Abraão, R.P. 2025. Análise de viabilidade do uso de coagulantes naturais no tratamento de águas de abastecimento público. Dissertação de

Gujarati, D.N.; Porter, D.C. 2011. Econometria Básica. 5ed. AMGH Editora, Porto Alegre, RS, Brasil.

Géron, A. 2021. Mão à Obra: Aprendizado de Máquina com Scikit-Learn, Keras & TensorFlow. 2ed. Alta Books, Rio de Janeiro, RJ, Brasil.

Hastie, T.; Tibshirani, R.; Friedman, J. 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2ed. Springer, New York, NY, EUA.

Libânio, M. 2010. Fundamentos de Qualidade e Tratamento de Água. 3ed. Editora Átomo, Campinas, SP, Brasil.

Montgomery, D.C.; Runger, G.C. 2016. Estatística Aplicada e Probabilidade para Engenheiros. 6ed. LTC, Rio de Janeiro, RJ, Brasil.

Sarmento, P.V.F. 2023. Avaliação do sistema de lavagem dos filtros de uma ETA de filtração direta descendente. Trabalho de Conclusão de Curso em Engenharia Civil. Universidade Federal do Rio Grande do Norte, Natal, RN, Brasil.

Article originating from the Final Course Project of the Specialization in Data Science and Analytics of the MBA USP/Esalq

To learn more about the course, click here and access the MBX Academy platform

Most recent

Economy, Investments And Banking

October 23, 2026

Financial Education, Behaviors and Biases in Financial Decision Making

October 22, 2026

Challenges and Possibilities of the First School Year of Children with ASD for Teaching Work

October 22, 2026

Consumer Journey in the Decision to Purchase Infoproducts in the Digital Environment

October 22, 2026

Psychosocial Risks and Mental Health at Work in a Banking Institution

October 22, 2026

Digital Observatory of the Amazon: Data Science Applied to the Analysis of Social, Economic, Environmental, and Health Indicators

October 22, 2026

Continuous Learning as a Factor of Organizational Growth in the Perception of Collaborators

October 22, 2026

Statistical Regression in Microgrids for Operational Performance Estimation: Campusgrid Case

October 22, 2026

Forecast of Aggregate Default in the Brazilian Financial System by Sarimax Model with Macroeconomic Variables

October 22, 2026

Stakeholder Engagement Factors in International Technology Transfer to a Public Hospital

Personal financial management represents a growing challenge, influenced by cognitive biases that affect decision-making, even in individuals with high knowledge. The present study analyzed the relationship between the level of financial education and the occurrence of behavioral biases in the financial decision-making of adults residing in Brazil. An applied, quantitative, and descriptive-correlational field survey was conducted by administering a structured questionnaire to 163 respondents. The instrument included sociodemographic variables, financial knowledge and habits, and hypothetical situations to identify cognitive biases. The results indicated that higher levels of financial education were associated with better financial control, saving, and investment practices, with significant correlations with income and schooling. However, the presence of behavioral biases (anchoring, loss aversion, scarcity, optimism/negativity, present bias, status quo, overconfidence, and mental accounting) persisted even among individuals with higher schooling and income, with no statistically significant association with the analyzed sociodemographic variables. It was concluded that financial education, although essential for financial organization and control, was not sufficient to neutralize the influence of cognitive biases. The incorporation of behavioral approaches into financial education programs is suggested.

Keywords: Financial behavior; Behavioral economics; Personal finance; Cognitive heuristics; Cognitive biases.

October 22, 2026

Challenges and Possibilities of the First School Year of Children with ASD for Teaching Work

The inclusion of children with Autism Spectrum Disorder (ASD) in Early Childhood Education presents significant challenges, given the difficulty of adapting to new environments and the intensity of stimuli. The objective was to analyze the teaching performance in Early Childhood Education in the initial schooling process of children with ASD. A case study was conducted, using narrative interview as a data production technique. The results revealed that the teaching performance was characterized by mediation and affection practices, with the flexibility of routine and the use of playful resources as essential strategies for the child’s development and sensory organization. The importance of the school support professional for the success of the pedagogical work was also highlighted. The child’s integral development was promoted through intentional teaching actions that prioritized environmental adaptation, strengthening of bonds, and attention to the specific needs of ASD. As a contribution, a guide of pedagogical strategies aimed at welcoming children with ASD in public daycare centers was developed.

Keywords: Early Childhood Education; School Inclusion; Teacher Narratives; Inclusive Pedagogical Practices; Autism Spectrum Disorder.

October 22, 2026

Consumer Journey in the Decision to Purchase Infoproducts in the Digital Environment

The expansion of e-commerce and technological transformation have driven the need to understand consumer behavior regarding infoproducts, whose perceived experience has become crucial for professional development. The study aimed to analyze the factors that influenced the purchase decision of infoproducts in the digital environment, considering the stages of the consumer journey. An applied, quantitative, and descriptive research was conducted through a field survey with 100 consumers from Serra Gaúcha. Data collection occurred via a structured questionnaire, using non-probabilistic sampling. The results revealed a qualified audience with strong “mobile-first” behavior. It was found that the availability of detailed information and social approval were the main attraction triggers in the pre-purchase phase. In the transactional and subsequent stages, the minimization of operational friction, the agility of immediate access, and system security proved crucial for conversion and satisfaction, although gaps in human support efficiency were identified. Retention was based on the trust generated by positive past experiences, overcoming the price factor. It was concluded that the infoproduct consumer journey operates as an integrated system, requiring alignment between technological infrastructure, content curation, and support humanization to ensure engagement.

Keywords: E-commerce; Consumer behavior; Consumer experience; Loyalty; Virtual business.

October 22, 2026

Psychosocial Risks and Mental Health at Work in a Banking Institution

Mental health in the workplace is a topic of growing relevance, impacting professional development and employee well-being. A study was conducted to identify aspects and situations that can influence absenteeism levels in a banking institution. The research involved 108 participants and used a structured questionnaire, based on the short version of COPSOQ II by Gonçalves (2021), which contained 45 closed Likert scale questions and two open-ended questions. Data were collected via an online platform and analyzed with a descriptive and quantitative approach. The results revealed a scenario that indicated the need for adjustments in the distribution of activities and in managers’ perception of behaviors and signs of disorders. Important evidence was identified in the participants’ open-ended responses. It was concluded that the study contributed to promoting the perception of a safe environment for mental health in the organization.

Keywords: Absences due to disorders; Professional development; Operational leadership; Medical leave; Mental health.

October 22, 2026

Digital Observatory of the Amazon: Data Science Applied to the Analysis of Social, Economic, Environmental, and Health Indicators

The state of Amazonas faced historical challenges in consolidating the Unified Health System (SUS), stemming from geographical barriers, socioeconomic inequalities, and structural limitations. This study described the development and implementation of a health information geoportal, designed to support monitoring, evaluation, and planning in the Amazonian context. A descriptive case study approach was adopted, based on documentary analysis and secondary data, covering the mapping of functionalities, technical infrastructure, and validation steps of the tool. The Portal was developed with open technologies and integrated multiple national databases, offering interactive dashboards, thematic maps, and a digital document repository. Among the results, highlighted were the georeferenced visualization of key indicators, the possibility of temporal comparative analyses, and the use of the platform in reviewing health plans and redirecting strategic actions. The portal can represent an advance in digital governance and evidence-based management, with potential for replication in other highly complex territories, provided it is accompanied by investments in technological infrastructure, professional training, and inter-institutional coordination.

Keywords: Amazon; Health Evaluation; Digital Health; Health Information Systems.

October 22, 2026

Continuous Learning as a Factor of Organizational Growth in the Perception of Collaborators

The impact of continuous learning and knowledge management on organizational growth was studied in a context of globalization and constant changes. The study’s objective was to analyze employees’ perception of learning culture and its importance for personal and professional development. Data were obtained through an anonymous survey, with a quantitative approach, using a form with “survey” type questions applied to 87 professionals from the technology, health, education, commerce, and services sectors. The results indicated that employees had a positive perception of the contribution of continuous learning to personal and organizational growth, recognizing its benefits for the development of new skills, innovation, and competitiveness. However, it was observed that the incentive for internal knowledge exchange and the offering of practical training still presented moderate levels of agreement. It was concluded that continuous learning significantly contributes to individual and organizational development, suggesting that companies should develop strategic policies for learning focused on new skills, aiming for greater competitive advantage and innovation.

Keywords: Continuous learning; Self-development; Organizational growth; Knowledge Management; Innovation.

October 22, 2026

Statistical Regression in Microgrids for Operational Performance Estimation: Campusgrid Case

A multiple statistical regression model was proposed to estimate the operational performance of UNICAMP’s CampusGrid microgrid, based on internal electrical quantities. The microgrid integrates photovoltaic generation, batteries, and a gas generator. Energy management system data were collected at five-minute intervals over one month. The Operational Reliability Index, defined as the ratio between supplied and demanded energy, was established as the dependent variable. The model was adjusted for the islanded operation mode, evaluating the impact of demand, state of charge, solar generation, and supplied energy. The results revealed high explanatory power, indicating that operational reliability depends on the interaction between supply and demand. It was observed that the nighttime period concentrated the highest rate of partial supply, attributed to the reduction in solar generation. It was concluded that multiple regression offers an interpretable and useful framework for microgrid monitoring and control strategy support.

Keywords: Battery storage; Photovoltaic generation; Reliability Index; Islanded operation; Energy Management System.

October 22, 2026

Forecast of Aggregate Default in the Brazilian Financial System by Sarimax Model with Macroeconomic Variables

Aggregate non-payment in the Brazilian financial system is a crucial indicator of credit risk, the prediction of which is regulated by CMN Resolutions n.° 4.557/2017 and 4.966/2021 for the prospective measurement of expected losses. Aggregate non-payment was modeled and predicted using the SARIMAX model, projecting its trajectory until December 2026 under optimistic, base, and pessimistic scenarios. 164 monthly observations (July/2012 to February/2026) and macroeconomic variables such as unemployment, Selic, IPCA, IBC-Br, and household debt were used. The specification with contemporaneous variables was selected based on information criteria and coefficient stability, and residual diagnostics confirmed statistical adequacy, with a MAPE of 3.12%. Historical non-payment ranged between 4.33% and 7.64%. The estimation identified unemployment (β = 0.2534; p < 0.001) and Selic (β = 0.2128; p < 0.001) as the main positive determinants, with strong temporal persistence (AR(1) = 0.8965). Selic showed increasing correlation with non-payment (r = 0.62 at lag 12), while unemployment demonstrated a contemporaneous effect (r = 0.33). Projections indicated non-payment between 6.30% and 7.98% in December 2026, with a range of 1.68 percentage points, highlighting direct implications for provisioning in financial institutions.

Keywords: Unemployment; Predictive modeling; Monetary policy; Loss provisioning; Time series.

October 22, 2026

Stakeholder Engagement Factors in International Technology Transfer to a Public Hospital

This study described the critical factors perceived for stakeholder engagement in international technology transfer in a public hospital, with a focus on planning. The objective was to describe these conditioning factors, according to the perception of professionals. A single case study was conducted, applying a questionnaire to 25 professionals and using content analysis, complemented by descriptive tabulations. The main obstacles identified were resistance to change (72%), funding (64%), lack of communication (60%), and bureaucracy (40%). Only 28% of respondents recognized the existence of adequate tools for stakeholder management, while 48% denied it and 24% did not know. Exploratory cross-tabulations indicated variations in the assessment of influence according to time of practice, but did not establish causal relationships. Lack of engagement was associated with delays, low adherence, waste of resources, communication failures, compromised knowledge absorption, and risks to patient safety. The conclusions were limited to the perceptions of the researched group and supported preliminary recommendations for intersectoral communication and coordination.

Keywords: Case study; Project Management; Health innovation; Stakeholders; Public sector.

Economy

October 19, 2026

End of the 6×1 scale: what do the numbers allow us to conclude?

Following the promulgation of the end of the 6×1 shift system, the debate on the shorter workday moves to implementation and requires distinguishing social benefits from economic costs. The end of the 6×1 shift system transitioned from legislative discussion to a constitutional change in Brazil. On October 16, 2026, the National Congress promulgated Constitutional Amendment No. 141/2026, originating from Proposal […]

Artificial Intelligence

October 16, 2026

Why study if AI exists?

When answers become easy, learning comes to mean more than just arriving at them. Why do I need to learn this if I can ask an artificial intelligence? This type of question has accompanied education for decades. Why learn an operation if a calculator exists? Why memorize information if it can be found […]

Tax Management

October 15, 2026

Pink tax and the gender of price

How different marketing treatments for men and women are incorporated by consumption taxation Imagine a shelf on which two razors of the same brand and intended for the same purpose are displayed side by side: one has dark packaging and promises strength, precision, and efficiency; the other comes in shades of pink or […]

Health

October 13, 2026

The missing link in health transformation

Why is innovation not enough to drive changes in organizations and health systems Digital transformation has become a strategic priority for health systems worldwide. Electronic health records, artificial intelligence, telemedicine, remote monitoring, and data analysis are now part of the strategic agenda of governments and health organizations. Paradoxically, […]

Marketing

October 09, 2026

Bitcoin or pets: what Artificial Intelligence would not see

A real-life consumer intelligence case shows what gets left out of the brief A few years ago, an American insurance company hired a specialized consumer intelligence firm to answer three questions: The insurer was also considering launching paid insurance in bitcoin. At the time, the consultancy’s workflow was as follows: the analyst created a query […]

School Management

October 06, 2026

The school is not a casino: when trading cards become currency in the playground

Why, for certain students, does school manage to offer so few experiences of achievement? The World Cup is over. Brazil left the competition, the school holidays came, the final was played and the football calendar moved on. It would be reasonable to imagine that, with the end of the tournament and the return to classes, […] would also begin

Energy Transition

September 30, 2026

Renewable energies: the Brazilian advantage

Brazil needs to invest in the capacity to transform natural resources into innovation, productivity, and development. Talking about energy is talking about development. Behind industry, transportation, services, cities, and increasingly artificial intelligence, there is an energy infrastructure that sustains the economy. Understanding a country’s energy matrix is understanding […]

Data Analysis

September 30, 2026

When the data changes, has reality changed?

An analysis of almost 20 million teaching positions-year between 2020 and 2025 shows how changes in population composition and record production can alter the interpretation of historical series Between 2020 and 2025, the number of formal teaching employment positions identified in RAIS (Annual Relation of Social Information), from the Ministry of Labor, […]

Artificial Intelligence

September 28, 2026

Artificial intelligence and the trends

Why do so many people join in on the fun with ChatGPT? I was never the trend person. I still am not. Some pass through my timeline, I see them, I find them interesting but not to the point of trying them out. This was the case, inclusive, with some recent waves of images made by artificial intelligence, like the 80s trend, the one that […]

Tax Management

September 01, 2026

Tax reform and estate planning in the countryside

Efficiency in managing taxes facilitates governance and allows for the organization of family succession. Rural wealth organization has become a strategic measure in light of the tax reform in Brazil, which came into effect this year. The planning of activities and rural wealth management, through tools such as the transition from an Individual to […]

Renata de Gaspari Valdejão Almeida

Artificial Intelligence

August 05, 2026

Inside the company and off the radar: the risks of Shadow AI

According to Microsoft, 75% of professionals already use artificial intelligence at work without company approval. The use of generative artificial intelligence is already part of the corporate routine. Tools like ChatGPT, Copilot, and other platforms help professionals produce texts, analyze data, create presentations, and accelerate tasks in practically all sectors. But this advance […]

Renata de Gaspari Valdejão Almeida

Strategy

July 02, 2026

The future as a competence

Academic interest reinforces the projection of scenarios as an essential tool for decision-making. While some companies are still trying to get the next step right, others are already working with multiple possible futures — and preparing for all of them. But after all, what does it mean to “think about the future”? Is it a trend, a strategy, or a new competence that […]

Renata de Gaspari Valdejão Almeida

Innovation

Technology

May 21, 2026

Agro SP Corridor: innovation, institutional articulation and future

Pecege commands the executive operation of the 400 km ecosystem activities that became known as the Brazilian agro Silicon Valley In 2025, in addition to taking over the management of the Piracicaba Technology Park, the Pecege Institute was also designated to command the executive operation of the State Agribusiness Innovation Corridor activities, the so-called […]

Education

April 27, 2026

How to turn a TCC into a business

New management of the Piracicaba Technology Park offers consulting to MBA graduates The new project director of the Piracicaba Technology Park (PTP), Alexandre Barreto, often says that one of the greatest rewards he has ever had in life was seeing his MBA USP/Esalq students structure companies from their final projects […]

Technology

March 20, 2026

The human repertoire in the age of AI

Critical thinking and creativity are irreplaceable in the work of a marketing professional Artificial Intelligence (AI) is capable of incredible feats, but it does not yet possess the judgment, empathy, intuition, and strategic creativity necessary to do the job of a good marketing professional. In this area, it is important to know how to use the tool to automate […]

Renata de Gaspari Valdejão Almeida

Agribusiness

Innovation

February 23, 2026

ESG as a growth strategy in a cooperative in RS

Santa Clara balances social and environmental responsibility with innovation Founded in 1911 by Italian immigrants in Carlos Barbosa, in the Serra Gaúcha region, Cooperativa Santa Clara is an example that it is possible to balance economic growth with social and environmental responsibility. From a small cheese production company, the organization has evolved into a […]

Renata de Gaspari Valdejão Almeida

Agribusiness

Innovation

January 22, 2026

Brazil free of Foot-and-Mouth Disease: what changes for Brazilian beef?

With a herd of over 200 million head of cattle, the country is currently the leader in exports. Brazil recently received, for the first time, the certification of country free of foot -and-mouth disease without vaccination, conferred by the World Organisation for Animal Health (WOAH). The seal strengthens the country’s position as a reliable supplier of meat for the […]

Renata de Gaspari Valdejão Almeida

Innovation

December 09, 2025

Innovation: the new cycle of the Piracicaba Technology Park

Instituto Pecege assumes management, betting on the creation of new businesses Starting in 2026, Instituto Pecege will assume the management of the Piracicaba Technology Park (PTP). Among its responsibilities will be the administration, operation, maintenance, and expansion of the park, in addition to fostering activities in innovation, entrepreneurship, and science and technology. The choice was made […]

Renata de Gaspari Valdejão Almeida

July 06, 2026

Large-Scale Architecture: DSR-SCRUM Change Management

Mônica Alessandra Guerios; Maria do Carmo Assis Todorov Abstract generated by ResumeAI, an artificial intelligence solution developed by Instituto Pecege focused on synthesis and writing. Architecture and urbanism are configured as essential bases in an increasingly complex and challenging urban space, where the intrinsic connection between social, environmental, and technological issues […]