Sürdürülebilir Kalkınma Amaçları
Yayınlar
- MakaleYalnız künye2026Scopus SJRQ1Innovative solutions for aquaculture: detecting fish diseases with hybrid deep learning model and explainable artificial intelligence
Utku, Anıl; Barut, Abdulkadir; Alofaysan, Hind
Early identification of fish diseases is critical to maintain aquaculture and minimize its financial burden. In the diagnosis of diseases, time is critical and scientists’ experience is imperative, which makes the artificial intelligence-based models necessary. It is intended by this study to integrate deep learning with explainable artificial intelligence methods to establish an artificial intelligence-powered framework for early detection of disease in fish. In this study, we developed a hybrid artificial intelligence system designed to detect diseases in freshwater fish by analyzing skin images. The primary objectives of the system are to minimize economic losses, prevent further disease spread, and ultimately increase aquaculture productivity. For this purpose, we used a dataset consisting of images from seven different disease categories, with 250 images in each class. A new hybrid model, Residual Network-50–Vision Transformer, was developed by integrating the strengths of Residual Network-50 and Vision Transformer architectures to improve classification accuracy. The proposed model was subjected to rigorous comparison with established architectures, including Visual Geometry Group 16, Mobile Convolutional Neural Network Version 2, Efficient Neural Network–Baseline Model B0, standalone Vision Transformer, and the original Residual Network-50. The results demonstrated that Residual Network-50–Vision Transformer outperformed the model, achieving an impressive 99.14% accuracy rate. Furthermore, the study employed local interpretable model-independent explanations to explain which image features most significantly influence the model’s classification decisions, thereby enhancing the interpretability and confidence in the model’s output. The application of such advanced image processing models in combination with explainable AI techniques demonstrates significant potential to support sustainable aquaculture by reducing disease outbreaks and associated financial losses.
AtıfScopus3OpenAlex2
İncele - MakaleAçık Erişim2026Scopus SJRQ1Quantifying agricultural resilience under climate variability: a data-driven climate resilience index for European cereal systems
Utku, Anil; Radulescu, Magdalena; Barut, Abdulkadir; Alofaysan, Hind
Climate variability and extreme weather events pose an increasingly serious threat to agricultural productivity in Europe. Although many studies have focused on the mean yield response to climate change, relatively few have attempted to offer a comprehensive, multi-dimensional view of agricultural resilience, separating long-term productivity trends from short-term climate-induced fluctuations. In this paper, a data-driven Climate Resilience Index is proposed to assess the resilience of European cereal systems under climate stress. Annual yield time series are decomposed into trend and anomaly components to identify interannual deviations driven by climate variability. Machine learning and deep learning algorithms, including RF, CatBoost, CNN, LSTM, TCN, and a TCN-LSTM hybrid model, are used to assess the predictive validity of climate extreme indices and persistence patterns. Among the evaluated models, the TCN-LSTM architecture achieved the highest predictive performance with 0.8347 R2, outperforming standalone temporal and ensemble-based models. The PCA-based exposure framework explained 68.4% of the total climate variability within the first principal component, indicating a highly concentrated climate-stress structure. Feature importance analyses further revealed that lagged yield anomalies and rolling volatility indicators were the dominant predictors of resilience dynamics. The findings show that temporal models perform better than traditional ensemble methods, emphasizing the significance of multi-year recovery mechanisms in anomaly evolution. To provide a consistent measure of exposure, principal component analysis is used to reduce correlated climate indicators into a multi-dimensional climate stress index. The CRI captures these three essential elements: climate exposure, yield variability, and recovery. The results at the country level show substantial variability across Europe, indicating that while exposure intensity is important, recovery dynamics are also critical to understanding resilience. The results also show that there are structurally distinct resilience profiles, and robustness tests indicate that country rankings are not sensitive to different weights and recovery functions. The results clearly show that recovery and adaptive capacity are critical to agricultural sustainability amid growing climate uncertainty. The CRI developed in this paper provides a clear, empirically valid framework for comparing resilience in agricultural systems.
AtıfScopus1OpenAlex2
İncele - MakaleAçık Erişim2026Scopus SJRQ2Federated agricultural yield forecasting under an Edge–Fog–Cloud framework: a multi-country privacy-preserving approach
Utku, Anıl; Barut, Abdulkadir; Alofaysan, Hind; Henni, Mohamed Djafar; Amoozegar, Azadeh
Predicting agricultural yields is crucial for ensuring global food security and adaptation to climate change. However, the centralized collection of agricultural data across countries might pose governance, privacy, and data sovereignty issues. This research presents a privacy-preserving model for predicting agricultural yields using federated learning within an edge-fog-cloud integrated architecture. The experiments have been performed on a European cereal production dataset for the period 1990–2022, using a time-aware forecasting scheme. Centralized, edge-only, federated, and hybrid learning techniques have been systematically compared to examine the influence of distributed optimization on forecasting performance. It can be seen that central classical machine learning algorithms have yielded the best predictive performance. Federated deep learning models, meanwhile, showed relatively poor forecasting accuracy compared to their centralized counterparts under a non-IID distribution of multi-country agricultural data. Edge-only learning, meanwhile, has yielded comparatively low generalization capabilities due to the absence of collaborative learning.