Yazar "Gunay, Mehmet Erdem" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Assisted recovery of mediterranean native fish species by removal of two established invasive alien species, Pterois miles and Diadema setosum
    (Academic Press Ltd- Elsevier Science Ltd, 2024) Huseyinoglu, M. F.; Jimenez, C.; Resaikos, V.; Arda, Y.; Beton, D.; Snape, R. T. E.; Gunay, Mehmet Erdem
    The introduction of alien species is probably one of the most important factors affecting native biodiversity in various regions of the world. The Mediterranean is considered the most affected sea in the world. Although many efforts to control several invasive alien species (IAS) have been carried out in the Mediterranean, complete success has not been obtained so far. In the eastern Mediterranean (Levantine Sea), the island of Cyprus is among the first places where marine species migrating across the Suez Canal are reported and known to have been established. To test whether native species are able to recover in the absence of IAS, removal experiments of two established IAS, the common lionfish Pterois miles and the long-spined sea urchin Diadema setosum, were carried out at two submerged rocky reefs in Cyprus where human activities are limited. A baseline period of three months was dedicated to characterizing the fish communities by visual censuses, followed by a middle period of four months of monthly removals which ended with the second and final characterization period of three months of the fish communities. The removals of D. setosum were very effective suggesting that the recolonization rate of the species is considerably low. The removals of lionfish seem to help the populations remain small, although recolonization rates are higher than D. setosum. Moreover, our results suggest that the removal of these two species helps native fish recover while conversely affecting other alien fish in a negative manner. Despite the amount of enough data, it is possible to preliminarily estimate the rate of removals. Monitoring of the two IAS along with the native flora and fauna is suggested in these two sites to identify seasonality and trends.
  • Küçük Resim Yok
    Öğe
    Predicting biodiesel properties and its optimal fatty acid profile via explainable machine learning
    (Pergamon-Elsevier Science Ltd, 2022) Suvarna, Manu; Jahirul, Mohammad Islam; Aaron-Yeap, Wai Hung; Augustine, Cheryl Valencia; Umesh, Anushri; Rasul, Mohammad Golam; Gunay, Mehmet Erdem
    The accurate prediction of biodiesel fuel properties and determination of its optimal fatty acid (FA) profiles is a non-trivial process. To this aim, machine learning (ML) based predictive models were developed for cetane number (CN) and cold filter plugging point (CFPP), where the extreme gradient boost (XGB) and random forest (RF) algorithms had the best performance with R-2 of 0.89 and 0.91 on the test data, respectively. A classifier model for oxidative stability (OS) was devised to predict if it would pass or fail the ASTM and EU limits, where the support vector classifier (SVC) had the highest accuracy of 0.93 and 0.77 for ASTM and EU limits. Causal analysis via Shapley and Accumulated Local Effects revealed the significance and correlation of FAs with the fuel properties. This eventually aided the determination of the optimal FA composition via evolutionary optimization, such that the properties would meet the ASTM and EU standards. This study presents an end-to-end ML framework including descriptive, predictive, causal and prescriptive analytics to predict biodiesel fuel properties as a function of its FA composition; and eventually prescribes the optimal FA composition necessary to ensure that the fuel properties meet the regulatory standards.(c) 2022 Elsevier Ltd. All rights reserved.