Although the complexity of physically-based models continues to increase, they still need to be calibrated. In recent years, there has been an increasing interest in using new satellite technologies and products with high resolution in model evaluations and decision-making. The aim of this study is to investigate the value of different remote sensing products and groundwater level measurements in the temporal calibration of a well-known hydrologic model i.e., Hydrologiska Bryåns Vattenbalansavdelning (HBV). This has rarely been done for conceptual models, as satellite data are often used in the spatial calibration of the distributed models. Three different soil moisture products from the European Space Agency Climate Change Initiative Soil Measure (ESA CCI SM v04.4), The Advanced Microwave Scanning Radiometer on the Earth Observing System (EOS) Aqua satellite (AMSR-E), soil moisture active passive (SMAP), and total water storage anomalies from Gravity Recovery and Climate Experiment (GRACE) are collected and spatially averaged over the Moselle River Basin in Germany and France. Different combinations of objective functions and search algorithms, all targeting a good fit between observed and simulated streamflow, groundwater and soil moisture, are used to analyze the contribution of each individual source of information.
Prediction of river discharge is important for water resources management. Engineers have developed many physical and mathematical models for prediction of river discharge. The fact that physical hydrological models are site specific and include many parameters, has led researchers to work on mathematical black-box models. In this study, the fuzzy time series (FTS) method was used in the prediction of river discharge. The proposed method, which is employed for the first time in hydrology, allows to fast decision-making mechanism. The proposed algorithm, FTS, is used along with continuous wavelet transform (CWT) method to improve prediction performance. CWT, can be used as pre-treatment technique, is able decompose concerned time series into several bands at different scales which allows to predict much more homogeneous series rather than complex flow discharge series. By considering various statistical success criteria, the wavelet transformed time series (WFTS) method performed quite high accurate predictions compared to the classical fuzzy time series method. Combining FTS with wavelet transform opens a new window in the fuzzy time series method applications that has ability to improve the prediction performance.
Son yıllarda artan insan nüfusu ile fosil yakıt kullanımı yaygınlaşmıştır. Enerji üretimi, ulaşım, ısınma gibi birçok kullanım alanına sahip fosil yakıtların yanması sonucunda atmosfere salınan zararlı maddelerin yoğunluğu hem kentsel hem de kırsal bölgelerde insan sağlığını tehdit edecek seviyelere ulaşabilmektedir. Lokal hava kalitesini muhafaza edecek önlemler almak ve kirleticilerin zararlarını en aza indirebilmek için ileriye yönelik emisyon tahminlerinde bulunmak büyük önem arz etmektedir. Çalışmamızda yanma sonucunda açığa çıkan önemli kirleticilerden PM10 ve SO2 maddelerinin mevcut günlük kayıtları kullanarak gelecekte olması muhtemel değerleri tahmin edilmeye çalışılmıştır. Erzincan ilinde 2016-2018 yılları arasında ölçülmüş toplam 651 adet veri kullanılarak bir model oluşturulmuştur. Model oluşturma aşamasında verilerin ilk 400 adeti eğitim, geriye kalan 251 adet veri doğrulama olmak üzere ikiye ayrılmıştır. Modeller K-En Yakın Komşuluk (KNN) algoritması kullanılarak kurulmuş ve modelleme başarısını arttırmak adına önişlem süreçlerinden biri olan dalgacık dönüşüm tekniği uygulanmıştır. Dalgacık dönüşümü ile oluşturulan modellerin, tahmin başarısını büyük derecede iyileştirdiği gözlemlenmiştir. Bu çalışma uygulaması basit makine öğrenmesi yöntemlerinden olan KNN'nin hava kirliliği tahmin modellerinde kullanılabileceğini kanıtlamıştır.
Tahminlerin finansal piyasalara uygulanmasına ilişkin kullanılan yöntemlerden bulanık mantık ve yapay sinir ağları üzerine son yıllarda artan bilimsel çalışmalar vardır. Bu çalışmada 2012-2016 yıllarına ait verilerle gelişmekte olan ülkeler Çin (Shangai), Hindistan (Nifty 50), Meksika (IPC-Meksika) ve İstanbul (BİST-100) ile gelişmiş ülkeler ABD (Nasdaq), İngiltere (FTSE-100), Almanya (DAX) ve Fransa (CAC-40) ele alınmıştır. Haftalık kapanış hisse senedi değerleri kullanılarak iki etkin modelin tahminde gösterdikleri performansları karşılaştırılmaya çalışılmıştır. Zaman serisi değerleri model oluşturma aşamasında %60 eğitim, %40 test olarak iki gruba ayrılmıştır. Sonuç olarak modellerin istatistiksel ve finansal performanslarını gösteren bazı kanıtlar elde edilerek birçok çalışmada belirtilen hisse senedi getirilerini tahmin etmek için çeşitli yapay zeka modellerini başarıyla uygulamanın umut verici sonuçlar verdiği gerçeğine ulaşılmıştır.
Although the complexity of physically based models continues to increase, they still need to be calibrated. In recent years, there has been an increasing interest in using new satellite technologies and products with high resolution in model evaluations and decision-making. The aim of this study is to investigate the value of different remote sensing products and groundwater level measurements in the temporal calibration of a well-known hydrologic model i.e. HBV. This has been rarely done for conceptual models as satellite data are often used in spatial calibration of the distributed models. Three different soil moisture products from ESA CCI SM v04.4, AMSR-E and SMAP, and total water storage anomalies from GRACE are collected and spatially averaged over the Moselle River Basin in Germany and France. Different combinations of objective functions and search algorithms all targeting a good fit between observed and simulated streamflow, groundwater and soil moisture are used to analyse the contribution of each individual source of information. Firstly, the most important parameters are selected using sensitivity analysis and then, these parameters are included in a subsequent model calibration. The results of our multi-objective calibration reveal substantial contribution of remote sensing products to the lumped model calibration even if their spatially distributed information is lost during the spatial aggregation. Inclusion of new observations such as groundwater levels from wells and remotely sensed soil moisture to the calibration improves the model’s physical behaviour while it keeps a reasonable water balance that is the key objective of every hydrologic model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.