Tea leaf diseases are among the most critical factors affecting the yield and quality of tea harvests. Due to climate change and widespread pesticide use in tea cultivation, these diseases have become more prevalent. As the demand for high-quality tea continues to rise, tea has assumed an increasingly prominent role in the global economy, thereby rendering the continuous monitoring of leaf diseases essential for maintaining crop quality and ensuring sustainable production. In this context, developing innovative and sustainable agricultural policies is vital. Integrating artificial intelligence (AI)-based techniques with sustainable agricultural practices presents promising solutions. Ensuring that the outputs of these techniques are interpretable would also provide significant value for decision-makers, enhancing their applicability in sustainable agricultural practices. In this study, advanced deep learning architectures such as ResNet50, MobileNet, EfficientNetB0, and DenseNet121 were utilized to classify tea leaf diseases. Since low-resolution images and complex backgrounds caused significant challenges, an ensemble learning approach was proposed to combine the strengths of these models. The generalization performance of the ensemble model was comprehensively evaluated through statistical cross-validation. Additionally, Grad-CAM visualizations demonstrated a clear correspondence between diseased regions and disease types on the tea leaves. Thus, the models could detect diseases under varying conditions, highlighting their robustness. The ensemble model achieved high predictive performance, with precision, recall, and F1-score values of 95%, 94%, and 94% across folds. The overall classification accuracy reached 96%, with a maximum standard deviation of 2% across all dataset folds. Additionally, Grad-CAM visualizations demonstrated a clear correspondence between diseased regions and specific disease types on tea leaves, confirming the ability of models to detect diseases under varying conditions accurately and highlighting their robustness.

İnsansız Hava Araçları (İHA) otomatik veya yarı otomatik uçuş prensibine sahip başlangıçta askeri amaçlar için kullanılan motorlu veya motorsuz hava araçlarıdır. Son yıllarda meydana gelen gelişmelerle birlikte İHA’lar, afet yönetim ve planlama, ormancılık, fotogrametrik ölçme, yol ve nehir gözlemleri, arazilerin üç boyutlu (3B) modellerinin üretilmesi gibi birçok ticari ve bilimsel çalışmalarda yaygın olarak kullanılmaya başlanmıştır. İHA’lara digital kameralarının entegre edilmesi yüksek çözünürlükte görüntülerin elde edilmesini sağlamıştır. Bu görüntülerin değerlendirilmesi zor ve zaman alıcı görünmesine rağmen dijital fotogrametri ile birlikte bu sorun ortadan kalkmakta ve objenin veya arazinin 3B yoğun nokta bulutu, Sayısal Yüzey Modeli (SYM) ve ortofoto görüntüleri üretilebilmektedir. Bu çalışmada, İTÜ Ayazağa Kampüsünde 60m, 80m ve 100m yüksekliklerinde uçuşlar gerçekleştirilerek 60m ve 80m yükseklikte 90°, 100m yükseklikte 45°, 60° ve 90° kamera açıları kullanılarak yüksek çözünürlüklü digital görüntüler elde edilmiştir ve alanın ortofotoları üretilmiştir. Çalışma bölgesinde jeodezik yöntemler kullanılarak önceden tesis edilmiş 5 adet yer kontrol noktası ile ortofoto görüntülerin doğrulukları test edilmiştir. Bu çalışma kapsamında hem farklı yüksekliklerin, hem de aynı yükseklikte farklı kamera açılarının üretilen ortofoto görüntünün doğruluğuna etkisi irdelenmiştir.

Numerous deep learning techniques have been explored in pursuit of achieving precise road segmentation; nonetheless, this task continues to present a significant challenge. Exposing shadows and the obstruction of objects are the most important difficulties associated with road segmentation using optical image data alone. By incorporating additional data sources, such as LiDAR data, the accuracy of road segmentation can be improved in areas where optical images are insufficient to segment roads properly. The missing information in spectral data due to the object blockage and shadow effect can be compensated by the integration of 2D and 3D information. This study proposes a feature-wise fusion strategy of optical images and point clouds to enhance the road segmentation performance of a deep learning model. For this purpose, high-resolution satellite images and airborne LiDAR point cloud collected over Florida, USA, were used. Eigenvalue-based and geometric 3D property-based features were calculated based on the LiDAR data. These optical images and LiDAR-based features were used together to train, end-to-end, a deep residual U-Net architecture. In this strategy, the high-level features generated from optical images were concatenated with the LiDAR-based features before the final convolution layer. The consistency of the proposed strategy was evaluated using ResNet backbones with a different number of layers. According to the obtained results, the proposed fusion strategy improved the prediction capacity of the U-Net models with different ResNet backbones. Regardless of the backbone, all models showed enhancement in prediction statistics by 1% to 5%. The combination of optical images and LiDAR point cloud in the deep learning model has increased the prediction performance and provided the integrity of road geometry in woodland and shadowed areas.

Deep learning architectures are widely used for road segmentation studies. Data sets reflect the characteristics of the study region in which they are generated. The models that are trained with the data sets are unable to accurately forecast the region outside the area covered by the data sets. That is why local data sets must be generated to meet the requirements of navigation, military activities, urban planning and health management applications where road data are indispensable. In this study, satellite images and corresponding mask images of Istanbul city at different zoom levels were generated via Google Map Platform. Trained models were produced using Deep Residual U-Net. This study consists of three parts. The first part includes training each zoom level, from 14 to 17, separately. The recall statistics of models were found as 95%, 94%, 92% and 86%, and corresponding F1-Score statistics were calculated as 95%, 95%, 92% and 86%, respectively. Next, consecutive training with priory weight and $L_0$ regularization on satellite images were tested to increase the prediction results. The consecutive model and $L_0$ regularization methods resulted in an increase in both recall and F1-Score by 2−3%. In the third part, a new model was generated by combining all images which were produced at different levels. The combined model was found successful for the prediction of roads in all zoom levels. Finally, the performance of these models trained with the Istanbul data set was compared with well-known DeepGlobe and Massachusetts road data sets. Hence, this study illustrated that generating all data sets specifically for the area of interest is crucial.

Accurate crop yield prediction is essential for stabilizing food supply chains and reducing the uncertainties in financial risks related to agricultural production. Yet, it is even more essential to understand how crop yield models make predictions depending on their relationship to Earth Observation (EO) indicators. This study presents a state-of-the-art explainable artificial intelligence (XAI) method to estimate corn yield prediction over the Corn Belt in the continental United States (CONUS). We utilize the recently introduced Kolmogorov–Arnold Network (KAN) architecture, which offers an interpretable alternative to the traditional Multi-Layer Perceptron (MLP) approach by utilizing learnable spline-based activation functions instead of fixed ones. By including a KAN in our crop yield prediction framework, we are able to achieve high prediction accuracy and identify the temporal drivers behind crop yield variability. We create a multi-source dataset that includes biophysical parameters along the crop phenology, as well as meteorological, topographic, and soil parameters to perform end-of-season and in-season predictions of county-level corn yields between 2016–2023. The performance of the KAN model is compared with the commonly used traditional machine learning (ML) models and its architecture-wise equivalent MLP. The KAN-based crop yield model outperforms the other models, achieving an R² of 0.85, an RMSE of 0.84 t/ha, and an MAE of 0.62 t/ha (compared to MLP: R² = 0.81, RMSE = 0.95 t/ha, and MAE = 0.71 t/ha). In addition to end-of-season predictions, the KAN model also proves effective for in-season yield forecasting. Notably, even three months prior to harvest, the KAN model demonstrates strong performance in in-season yield forecasting, achieving an R² of 0.82, an MAE of 0.74 t/ha, and an RMSE of 0.98 t/ha. These results indicate that the model maintains a high level of explanatory power relative to its final performance. Overall, these findings highlight the potential of the KAN model as a reliable tool for early yield estimation, offering valuable insights for agricultural planning and decision-making.