20 yıl öncesine kadar teknolojinin insanlara sunduğu fırsatlar oldukça sınırlıydı. Günden güne evrensel ilerleme aracı olarak kullanılan bilişim teknolojileri bu fırsatları artırarak, küreselleşen dünyanın vazgeçemediği bir unsur haline gelmiştir. Günümüzde dijitalleşmenin artması ile birlikte teknolojinin hızına yetişmek oldukça zordur. Dijital çağ olarak adlandıran teknoloji yüzyılı, bireylerin hayatlarını kolaylaştırırken yenilikler sunarak teknolojiye bağımlı bireyler haline dönüştürmüştür. Bilişim teknolojinin gelişmesi ile örgütler teknolojinin sunduğu araçları kullanarak çağın sunduğu olanakları fırsata dönüştürerek hem ulusal hem de uluslararası bir ilerlemenin parçası olmuştur. Örgütler 21.yüzyıl ile hızlı bir dönüşüme girerek teknolojinin sunduğu araçları bünyelerine entegre etmişlerdir. Dolayısıyla, Dijitalleşme ve Bilişim teknolojilerinin çalışanlar üzerinde olumlu ve olumsuz etkilerinin olduğu görülmektedir. Çalışmanın amacı, dijitalleşme sürecinde meydana gelen dönüşümün çalışanların üzerinde bıraktığı etkiyi yapılan çalışmalar ışığında inceleyerek, alanyazına katkı sağlamaktır.

Managing the capacity of lithium-ion batteries (LiBs) accurately, particularly in large-scale applications, enhances the cost-effectiveness of energy storage systems. Less frequent replacement or maintenance of LiBs results in cost savings in the long term. Therefore, in this study, AdaBoost, gradient boosting, XGBoost, LightGBM, CatBoost, and ensemble learning models were employed to predict the discharge capacity of LiBs. The prediction performances of each model were compared based on mean absolute error (MAE), mean squared error (MSE), and R-squared values. The research findings reveal that the LightGBM model exhibited the lowest MAE (0.103) and MSE (0.019) values and the highest R-squared (0.887) value, thus demonstrating the strongest correlation in predictions. Gradient boosting and XGBoost models showed similar performance levels but ranked just below LightGBM. The competitive performance of the ensemble model indicates that combining multiple models could lead to an overall performance improvement. Furthermore, the study incorporates an analysis of key features affecting model predictions using SHAP (Shapley additive explanations) values within the framework of explainable artificial intelligence (XAI). This analysis evaluates the impact of features such as temperature, cycle index, voltage, and current on predictions, revealing a significant effect of temperature on discharge capacity. The results of this study emphasize the potential of machine learning models in LiB management within the XAI framework and demonstrate how these technologies could play a strategic role in optimizing energy storage systems.

Li-ion batteries are important in modern technology, especially for drones, due to their high energy density, long cycle life, and lightweight properties. Predicting their performance is crucial for enhancing drone flight safety, optimizing operations, and reducing costs. This involves using advanced techniques like machine learning (e.g., Convolutional Neural Network-CNNs, Recurrent Neural Network-RNNs), statistical modeling (e.g., Kalman Filtering), and explainable AI (e.g., SHAP, LIME, PDP) to forecast battery behavior, extend battery life, and improve drone efficiency. The study aims to develop a CNN-RNN-based ensemble model, enhanced with explainable AI, to predict key battery metrics during drone flights. The model’s predictions will aid in enhancing battery performance via continuous, data-driven monitoring, improve drone safety, optimize operations, and reduce greenhouse gas emissions through advanced recycling methods. In the present study, comparisons are made for the behaviors of two different drone Li-ion batteries, numbered 92 and 129. The ensemble model in Drone 92 showed the best performance with MAE (0.00032), RMSE (0.00067), and R² (0.98665) scores. Similarly, the ensemble model in Drone 129 showed the best performance with MAE (0.00030), RMSE (0.00044), and R² (0.98094) performance metrics. Similar performance results are obtained in the two predictions. However, drone 129 has a minimally lower error rate. When the Partial Dependence Plots results, which are one of the explainable AI (XAI) techniques, are interpreted with the decision tree algorithm, the effect of the Current (A) value on the model estimations in both drone flights is quite evident. When the current value is around −4, the model is more sensitive and shows more changes. This study will establish benchmarks for future research and foster advancements in drone and battery technologies through extensive testing.

The aim of the study is to review XAI studies in terms of their solutions, applications and challenges in renewable energy and resources. The results have shown that XAI really helps to explain how the decisions are made by AI models, to increase confidence and trust to the models, to make decision mode reliable, show the transparency of decision-making mechanism. Even if there have been a number of solutions such as SHAP, LIME, ELI5, DeepLIFT, Rule Based Approach of XAI methods, a number of problems in metrics, evaluations, performance and explanations are still specific, and require domain experts to develop new models or to apply available techniques. It is hoped that this article might help researchers to develop XAI solutions in their energy applications and improve their AI approaches for further studies.

Integrating renewable energy sources with new technologies such as artificial intelligence (AI) is important to balance energy supply and demand. The predictability of variable energy sources, such as solar energy, plays an important role in maintaining the stability and efficiency of power grids. This study examines the use of various algorithms in AI applications within renewable energy systems. The study critically evaluates existing methods and proposes an innovative approach for AI prediction in solar energy systems using advanced machine learning techniques. It focuses on the effectiveness of MLP, Ridge, and RF algorithms in forecasting Direct Current (DC). The results showed that the RF algorithm achieved the highest R² value (0.9999) and the lowest error RMSE (0.0024) and MAE (0.0006) measurements to demonstrate the superior ability of the models to explain variance in the data and make accurate predictions. In addition, the model developed with SHAP and LIME explainable AI algorithms is interpreted.

The use of artificial intelligence (AI) approaches, one of the most significant technological advances of the 21st century, to determine the diode parameters that can be obtained from Schottky diode characterization allows data to be collected, processed, analyzed, and results obtained faster than ever before, with high accuracy. It also supports the development of a selection and modeling tool for future studies and, most importantly, facilitates modeling implementation with faster and fewer experimental results. In this context, this study presents a machine learning model to predict diode parameters from current–voltage (I-V) measurements of polyethyleneimine-functionalized graphene quantum dots (GQDs)-based Schottky hybrid diode. This study used K-Nearest Neighbor, Random Forest (RF), Multilayered Perceptron, and Support Vector Machine algorithms. In research, the lowest model error of each model was compared, and the performance of the models obtained was evaluated. In addition, out of 30 diodes on the fabricated structure, the diode with the best rectification ratio (RR) was identified within a few seconds using machine learning, verified to be the same as the diode selected by the researchers, and the optimal estimation of RR and ideality factor was made from the diode parameters using the thermionic emission method. The experimental results were compared with machine learning models. Among these algorithms, the RF algorithm performed best with a mean square error value of 4.1 E-05 and an R-squared value of 0.999998. The success of RF depends on the characteristics of the dataset used, its size, and data distribution. The success rate of the RF algorithm is more successful in the 200 data sets used in this study. RF reduces overfitting by taking the average of multiple decision trees and is less sensitive to noise and outliers in the data. The results obtained will allow the development of a selection and modeling tool for future studies and, most importantly, facilitate modeling faster and with fewer experimental results, enabling the integration of AI into science.