Mehmet Furkan Celik

Dr. Mehmet Furkan Celik

Natural Resources Department, University of Twente, Enschede, The Netherlands
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Mehmet Furkan CelikMehmet Furkan Celik
Mehmet Furkan Celik
Mustafa Serkan IsikMustafa Serkan Isik
Mustafa Serkan Isik
Onur YuzugulluOnur Yuzugullu
Onur Yuzugullu
NFNoura Fajraoui
Noura Fajraoui
Esra ErtenEsra Erten
Esra Erten
Soil moisture (SM) is an important biophysical parameter by which to evaluate water resource potential, especially for agricultural activities under the pressure of global warming. The recent advancements in different types of satellite imagery coupled with deep learning-based frameworks have opened the door for large-scale SM estimation. In this research, high spatial resolution Sentinel-1 (S1) backscatter data and high temporal resolution soil moisture active passive (SMAP) SM data were combined to create short-term SM predictions that can accommodate agricultural activities in the field scale. We created a deep learning model to forecast the daily SM values by using time series of climate and radar satellite data along with the soil type and topographic data. The model was trained with static and dynamic features that influence SM retrieval. Although the topography and soil texture data were taken as stationary, SMAP SM data and Sentinel-1 (S1) backscatter coefficients, including their ratios, and climate data were fed to the model as dynamic features. As a target data to train the model, we used in situ measurements acquired from the International Soil Moisture Network (ISMN). We employed a deep learning framework based on long short-term memory (LSTM) architecture with two hidden layers that have 32 unit sizes and a fully connected layer. The accuracy of the optimized LSTM model was found to be effective for SM prediction with the coefficient of determination (R2) of 0.87, root mean square error (RMSE) of 0.046, unbiased root mean square error (ubRMSE) of 0.045, and mean absolute error (MAE) of 0.033. The model’s performance was also evaluated concerning above-ground biomass, land cover classes, soil texture variations, and climate classes. The model prediction ability was lower in areas with high normalized difference vegetation index (NDVI) values. Moreover, the model can better predict in dry climate areas, such as arid and semi-arid climates, where precipitation is relatively low. The daily prediction of SM values based on microwave remote sensing data and geophysical features was successfully achieved by using an LSTM framework to assist various studies, such as hydrology and agriculture.

9 August 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
Mehmet Furkan CelikMehmet Furkan Celik
Mehmet Furkan Celik
Mustafa Serkan IsikMustafa Serkan Isik
Mustafa Serkan Isik
GTGulsen Taskin
Gulsen Taskin
Esra ErtenEsra Erten
Esra Erten
GCGustau Camps-Valls
Gustau Camps-Valls
Cotton is under the threat of climate and ecosystem change, and has an essential role in the global textile industry. This makes its yield prediction essential for both economics and sustainability. The potential cotton yield can be predicted by integrating climatic factors, soil parameters, and biophysical parameters observed by high temporal & spatial resolution remote sensing satellites. This study used a multisource dataset to create an explainable and accurate predictive model for cotton yield prediction over the continental US (CONUS). A recently proposed glass-box method called Explainable Boosting Machine (EBM), which provides transparency, reliability, and ease of interpretation, was implemented. Accuracy performance was compared with common machine learning (ML) methods for predicting cotton yields. The EBM showed higher accuracy against other glass-box methods and competitive results with black-box models. With the help of the EBM, the importance of individual features and their pairwise interactions was revealed without applying any post-hoc methods. The study findings showed that the precipitation (P), enhanced vegetation index (EVI), and leaf area index (LAI) are the three most important dynamic features. The dynamic features are the driver of the created model with 78% of the overall feature importance, followed by pairwise interactions of the features with 16% contribution. Lastly, static features contribute 6% to the overall feature importance. The study highlights the importance of using multi-source data and interactions of the input features and providing an interpretable model to understand the inner dynamics of cotton yield predictions.

29 December 2023 in Water Resources Research
Verified
Journal Article
Open access
Oral YagciOral Yagci
Oral Yagci
VKV. S. Özgur Kirca
V. S. Özgur Kirca
VKVasileios Kitsikoudis
Vasileios Kitsikoudis
CWCatherine Wilson
Catherine Wilson
Mehmet Furkan CelikMehmet Furkan Celik
Mehmet Furkan Celik
CSCaner Sertkan
Caner Sertkan
Flume experiments were conducted to comprehend the impact of different patterns of an emergent vegetation patch on the flow field and the scour process in natural rivers. Velocity measurements, flow visualization, and scour tests were undertaken around different vegetation patch patterns, which were simulated inspired by the expansion process of a typical instream vegetation. The patch expansion process was idealized with an initially circular patch of rigid emergent stems becoming elongated due to positive and negative feedbacks. The expansion of the vegetation patch was considered to occur in three stages, in which the density of the patch from the previous stage was increased while the patch was also elongated by connecting at its downstream side with another sparser vegetation patch. These stages were replicated succesively by increasing the density and elongating the patch. In this way, two processes (i.e., elongation and decrease in permeability), which usually have hydrodynamically opposite effects on flow fields, were simulated at the same obstruction. Despite generally elongated obstacles being streamlined bodies, the morphometric analysis obtained by laser scanner revealed that streamlined elongation of permeable patches amplifies global scour and enhances localization of the local scour hole. This situation implies that as the patch expands, in the wake region, the steady‐wake region becomes shorter, turbulence diminishes, lateral shear stress enhances, and deposition cannot occur far from the patch. Consequently, as the patch expands, the hydrodynamic consequences may restrict further patch expansion after a certain length/density.

1 December 2017 in Geomatik
Verified
Journal Article
Open access
PDF file
Ozan OzturkOzan Ozturk
Ozan Ozturk
BBBurhan Baha Bilgilioğlu
Burhan Baha Bilgilioğlu
Mehmet Furkan CelikMehmet Furkan Celik
Mehmet Furkan Celik
Süleyman Sefa BilgilioğluSüleyman Sefa Bilgilioğlu
Süleyman Sefa Bilgilioğlu
RURaşit ULUĞ
Raşit ULUĞ
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.

18 July 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Mustafa Serkan IsikMustafa Serkan Isik
Mustafa Serkan Isik
Ozan OzturkOzan Ozturk
Ozan Ozturk
Mehmet Furkan CelikMehmet Furkan Celik
Mehmet Furkan Celik
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.