Use of decision tree and artificial neural network approaches to model presence/absence of <i>Telestes muticellus</i> in piedmont (North‐Western Italy)

Tirelli, Tina; Pessani, Daniela

doi:10.1002/rra.1199

Cited by 24 publications

(6 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Squalius lucumonis is an endemic species with a distribution limited to three river basins in Central Italy [29,30]; the species is listed as endangered on the International Union for Conservation of Nature (IUCN) red list of threatened species [31], and the progressive reduction of the species range is due to habitat alterations and water withdrawals [30]. Telestes muticellus is endemic to Northern and Central Italy; it prefers moderately cool waters in upper stream reaches [32]. Padogobius nigricans is a species endemic to Central Italy.…”

Section: Introductionmentioning

confidence: 99%

Endemic Freshwater Fish Range Shifts Related to Global Climate Changes: A Long-Term Study Provides Some Observational Evidence for the Mediterranean Area

Carosi

Padula²,

Ghetti³

et al. 2019

Water

View full text Add to dashboard Cite

Climate changes will lead to a worsening of the ecological conditions, in terms of hydrological instability and rising water temperatures, of the Mediterranean rivers. Freshwater fishes inhabiting this area can be threatened in the near future by accelerating drought and decreased ecological connectivity. The main aim of the research was to analyze changes in the distribution of the endemic freshwater fishes Padogobius nigricans, Squalius lucumonis and Telestes muticellus in the Tiber River basin (Italy), within a proven period of climate warming, in terms of increasing water temperature and droughts. A multivariate analysis was conducted using fish and environmental data collected in 117 sites over the years 1990–2017. For the three species, population abundance, age structure and body condition were analyzed. Detectability, occupancy, local extinction and colonization processes were also examined. We showed that S. lucumonis and T. muticellus have shifted their distributions upstream, likely in order to reach their thermal optimum. Padogobius nigricans did not move upstream significantly, since the species is characterized by limited vagility and thus a low dispersal capability in a context of high river fragmentation. In the study area, elevation and river barriers seem to play a key role in extirpation and colonization processes; for S. lucumonis and T. muticellus the extinction probability decreased with increasing altitude, while for P. nigricans the colonization probability decreased with an increasing degree of river fragmentation. These results highlight how species-specific dispersal ability can lead to varying adaptability to climate change.

show abstract

Section: Introductionmentioning

confidence: 99%

Endemic Freshwater Fish Range Shifts Related to Global Climate Changes: A Long-Term Study Provides Some Observational Evidence for the Mediterranean Area

Carosi

Padula²,

Ghetti³

et al. 2019

Water

View full text Add to dashboard Cite

show abstract

“…Examples include boosted regression trees [63], random forests [48], and support vector machines [58]. In addition, neural networks have been used for species distribution modeling since well before the deep learning era [37,139,183,206].…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Species Distribution Modeling for Machine Learning Practitioners: A Review

Beery

Cole

Parker

et al. 2021

ACM SIGCAS Conference on Computing and Sustainable Societies (COMPASS)

View full text Add to dashboard Cite

Figure 1. Species distribution models describe the relationship between environmental conditions and (actual or potential) species presence. However, the link between the environment and species distribution data can be complex, particularly since distributional data comes in many different forms. Above are four different sources of distribution data for the Von Der Decken's Hornbill [11]: (from left to right) raw point observations, regional checklists, gridded ecological surveys, and data-driven expert range maps. All images are from Map of Life [101].

show abstract

“…Here complex classifier is defined as machine learning classifiers such as RF, SVM, ANN and KNN which have a number of parameters and difficult to interpret. The classifier performance was compared based on the model evaluation parameters such as classification accuracy (CCI), Cohen's kappa coefficient (k), sensitivity, specificity and receiver-operating-characteristics (ROC) (Saberioon et al 2018;Tirelli and Pessan 2009;Mansbridge 2018). Based on performance, the best classifier model was selected and further used for identifying the important habitat parameters for Chanda nama presence/absence (prediction) in the Krishna river.…”

Section: Methodsmentioning

confidence: 99%

Physicochemical Habitat Traits Preferred by Small Indigenous Fish (Chanda Nama ) in Indian River Discerning through Machine Learning

Raman

Das

Manna

et al. 2021

Preprint

View full text Add to dashboard Cite

Physicochemical traits of river influence the habitat of fish species in aquatic ecosystems. Fish showed a complex relationship with aquatic factors in river. Machine learning (ML) modeling is a useful tool to established relationship between complex systems. This study identified the preferred habitat indicators of Chanda nama (a small indigenous fish), in the Krishna River, of peninsular India, using machine learning modeling. Data were observed on Chanda nama fish distribution (presence/absence) and associated ten physical and chemical parameters of water at 22 sampling sites on the river during year 2001-02. Machine learning models such as random forest (RF), artificial neural network (ANN), support vector machine (SVM), k-nearest neighbors (KNN) used for the classification of Chanda nama distribution in the river. The ML model efficiency was evaluated using classification accuracy (CCI), Cohen’s kappa coefficient (k), sensitivity, specificity and receiver-operating-characteristics (ROC). Results showed that random forest is the best model with 82% accuracy, CCI (0.82), k (0.55), sensitivity (0.57), specificity (0.76) and ROC (0.72) for Chanda nama distribution (presence/absence) in the Krishna River. Random Forest model identified three preferred physicochemical habitat traits like altitude, temperature and depth for Chanda nama distribution in the Krishna River, India. This study will be helpful for researcher and policy maker to understand the important habitat physicochemical traits for sustainable management of small indigenous fish (Chanda nama ) in the river system.

show abstract

Use of decision tree and artificial neural network approaches to model presence/absence of Telestes muticellus in piedmont (North‐Western Italy)

Cited by 24 publications

References 113 publications

Endemic Freshwater Fish Range Shifts Related to Global Climate Changes: A Long-Term Study Provides Some Observational Evidence for the Mediterranean Area

Endemic Freshwater Fish Range Shifts Related to Global Climate Changes: A Long-Term Study Provides Some Observational Evidence for the Mediterranean Area

Species Distribution Modeling for Machine Learning Practitioners: A Review

Physicochemical Habitat Traits Preferred by Small Indigenous Fish (Chanda Nama ) in Indian River Discerning through Machine Learning

Contact Info

Product

Resources

About