Generalized Linear Latent Variable Models for Multivariate Count and Biomass Data in Ecology

In this paper we consider generalized linear latent variable models that can handle overdispersed counts and continuous but non-negative data. Such data are common in ecological studies when modelling multivariate abundances or biomass. By extending the standard generalized linear modelling framework to include latent variables, we can account for any covariation between species not accounted for by the predictors, notably species interactions and correlations driven by missing covariates. We show how estimation and inference for the considered models can be performed efficiently using the Laplace approximation method and use simulations to study the finite-sample properties of the resulting estimates. In the overdispersed count data case, the Laplace-approximated estimates perform similarly to the estimates based on variational approximation method, which is another method that provides a closed form approximation of the likelihood. In the biomass data case, we show that ignoring the correlation between taxa affects the regression estimates unfavourably. To illustrate how our methods can be used in unconstrained ordination and in making inference on environmental variables, we apply them to two ecological datasets: abundances of bacterial species in three arctic locations in Europe and abundances of coral reef species in Indonesia.Supplementary materials accompanying this paper appear on-line.     

Models for Jointly Estimating Abundances of Two Unmarked Site-Associated Species Subject to Imperfect Detection

In ecological field surveys, it is often of interest to estimate the abundance of species. It is frequently the case that unmarked animals are counted on different sites over several time occasions. A natural starting point to model these data, while accounting for imperfect detection, is by using Royle’s N-mixture model (Biometrics 60:108–115, 2004). Subsequently, many multivariate extensions have been proposed to model communities as a whole. However, these approaches are used to study species richness and other community-level variables and do not focus on the relationship between two site-associated species. Here, we extend the N-mixture modelling framework to model two site-associated species abundances jointly and propose to measure the influence of one species’ abundance on the populations of the other and study how this changes over time and space. By including a new parameter in the abundance distribution of one of the species, linking it to abundance of the other, our proposed model treats extra variability as an effect induced by an associated species’ abundance and allows one to study how environmental covariates may affect this. Using results from simulation studies, we show that the model is able to recover true parameter estimates. We illustrate our approach using data from bald eagles and mallards obtained in the 2015 survey of the North American Breeding Bird Survey. By using the joint model, we were able to separate overdispersion from mallard-induced variability and hence what would be accounted for with a dispersion parameter in the univariate framework for the eagles was explained by covariates related to mallard abundance in the joint model. Our approach represents an attractive, yet simple, way of modelling site-associated species populations jointly. Conservation ecologists can use the approach to devise management strategies based on the strength of association between species, which may be due to direct interactions and/or environmental effects affecting both species’ populations. Also, mathematical ecologists can use this framework to develop tools for studying population dynamics under different scenarios. Supplementary materials accompanying this paper appear on-line.     

A biodiversity monitoring framework for practical conservation of grasslands and shrublands

Comprehensive and standardized biodiversity monitoring schemes are needed to build scientifically sound decision-making tools for biodiversity conservation. Based on a thorough review of published literature, we propose a novel biodiversity monitoring framework to unify conservation theory and practice. The framework is built on the inter-connection among different types of indicators, and on the systematic articulation of their relationships into seven indicator approaches. Semi-natural grasslands and shrublands in Europe, which still lack a common biodiversity monitoring scheme, are used as a model for the framework. Different biotic indicators have been widely used to estimate the state of biodiversity, but we integrate these with biodiversity drivers, i.e. factors driving changes in biodiversity, to track biodiversity response to environmental changes. Precise information on biodiversity drivers (e.g. past and present management or disturbance regimes, environmental conditions, landscape patterns) has an effective indicator value, but this is often not taken into account in monitoring schemes. Our framework can be used to detect gaps in available data, translate indicator systems into practical conservation, identify combined sets of indicators to monitor biodiversity in target habitats, and recognize most suitable surrogates when information for some indicators is missing. We also take into account the effect of regional species pools in order to consider large-scale historical and biogeographical processes. We propose general guidelines to create validate and launch biodiversity monitoring frameworks for target habitats in the light of current examples of biodiversity conservation schemes (e.g. Natura 2000 in Europe).     

Conventional Harvest Index Methods may Overestimate Biomass and Nutrient Removal from Abscising Crop Species

ABSTRACT

Harvest index (HI) is conventionally measured using end-of-season biomass, but leaf abscission during crop growth can represent a substantial portion of total crop biomass for several species. A field study was conducted in Florida, USA, to determine the accuracy of conventional and alternative HI methods using sesame (Sesamum indicum L.) as a model species and to assess biomass and nutrient contributions from abscised leaves. Seed and nutrient HI was determined from three cultivars using the following four methods: (1) total biomass method that included both end-of-season and seasonal abscised biomass; (2) conventional method based solely on end-of-season biomass; (3) early-bloom method in which biomass collected during early-bloom stage was used as the nonseed biomass component; (4) mid-bloom method where biomass from mid-bloom stage was used for nonseed biomass. Early- and mid-bloom methods overestimated all HI and underestimated biomass and nutrient return to the soil. Most nutrient HI based on the conventional method was higher than the values based on the total biomass method. Compared to the total biomass method, the conventional method underestimated biomass and nutrient return to soil per ha by 714.8 kg biomass, 28.5 kg nitrogen, 3.6 kg phosphorus, 34.7 potassium, 4.6 magnesium, 25.7 calcium, 3.4 kg sulfur, 26.5 g boron, 361 g zinc, 25.9 g manganese, 527.2 g iron, and 18.7 g copper. Including abscised leaves when determining HI may not be feasible in field experiments due to labor constraints but is an option when measuring HI for species under similar management at regional scales to improve estimates of nutrient cycling.     

Nonparametric Threshold Model of Zero-Inflated Spatio-Temporal Data with Application to Shifts in Jellyfish Distribution

There is increasing scientific interest in studying the spatial distribution of species abundance in relation to environmental variability. Jellyfish in particular have received considerable attention in the literature and media due to regional population increases and abrupt changes in distribution. Jellyfish distribution and abundance data, like many biological datasets, are characterized by an excess of zero counts or nonstationary processes, which hampers their analyses by standard statistical methods. Here we further develop a recently proposed statistical framework, the constrained zero-inflated generalized additive model (COZIGAM), and apply it to a spatio-temporal dataset of jellyfish biomass in the Bering Sea. Our analyses indicate systematic spatial variation in the process that causes the zero inflation. Moreover, we show strong evidence of a range expansion of jellyfish from the southeastern to the northwestern portion of the survey area beginning in 1991. The proposed methodologies could be readily applied to ecological data in which zero inflation and spatio-temporal nonstationarity are suspected, such as data describing species distribution in relation to changes of climate-driven environmental variables. Some supplemental materials including an animation of jellyfish annual biomass and web appendices are available online.     

Time Matters: the Toxicity of Zinc Oxide Nanoparticles to <Emphasis Type="Italic">Lemna minor</Emphasis> L. Increases with Exposure Time

The use of zinc oxide nanoparticles (nano-ZnO) has rapidly increased in recent years, and this has triggered the need for versatile toxicity tests that can be used to test a range of different exposure scenarios. Acute exposure studies, using a variety of plant species, have overwhelmingly demonstrated nano-ZnO-induced toxicity, but substantial differences in the degree of phytotoxicity are reported in different studies. Here, we analysed the role of exposure time in determining the variation in phytotoxic effects. Using the model species Lemna minor, the effects of short-term (24 h), standardised (1 week) and chronic (up to 6 weeks) nano-ZnO exposure were compared. Nano-ZnO effects on Lemna minor growth indicators (biomass growth rate, root length), chlorophyll content and photosynthetic efficiency were measured. Rapid inhibitory effects of nano-ZnO on the maximal quantum yield of photosystem II could be measured after just 24-h exposure. Standardised (1 week) experiments revealed phytotoxic effects on Lemna minor biomass growth. More severe inhibitory effects on growth developed gradually over 4 to 6 weeks exposure to nano-ZnO, and these were qualitatively associated with increased zinc content in the plant. Such dynamics of nano-ZnO toxicity have not been elucidated before, and this study emphasises the importance of exposure time in studies of nanoparticle toxicity. We conclude that short-term, standardised experiments can potentially underestimate the environmental phytotoxicity, which may result from chronic exposure to nano-ZnO.     

Plant biomass management impacts on short-term soil phosphorus dynamics in a temperate grassland

The objective of this study was to quantify the combined effects of long-term plant biomass retention/removal and environmental conditions on soil microbial biomass phosphorus (P), bioavailable P, and acid phosphomonoesterase activity. Topsoil samples (0–2.5 and 2.5–5 cm) were collected from replicate field-based plots that had been maintained under contrasting plant biomass retention and removal regime for 21 years. Samples were collected on 14 occasions over a 17-month period and assessed for microbial P, bioavailable P, and phosphomonoesterase activity. All P measurements were consistently and significantly higher under plant biomass retention compared with biomass removal. Temporal variations in microbial P and phosphomonoesterase activity were evident in top soil (0–2.5 cm) and were driven by environmental conditions, mainly soil moisture, rainfall, and potential evapotranspiration, while bioavailable P had no temporal variation. Detailed analysis of microbial P data for the top 2.5-cm soil depth revealed that annual P flux through this pool was two times greater under biomass retention (10.3 kg P ha^?1 year^?1) compared with plant biomass removal (5.0 kg P ha^?1 year^?1). Similar and consistent trends were observed in soil from 2.5- to 5-cm sampling depth; however, differences were not significant. The findings of this study confirm the importance of the microbial biomass in determining the bioavailability of P in temperate grassland systems.     

Are hotspots of evolutionary potential adequately protected in southern California?

Reserves are often designed to protect rare habitats, or “typical” exemplars of ecoregions and geomorphic provinces. This approach focuses on current patterns of organismal and ecosystem-level biodiversity, but typically ignores the evolutionary processes that control the gain and loss of biodiversity at these and other levels (e.g., genetic, ecological). In order to include evolutionary processes in conservation planning efforts, their spatial components must first be identified and mapped. We describe a GIS-based approach for explicitly mapping patterns of genetic divergence and diversity for multiple species (a “multi-species genetic landscape”). Using this approach, we analyzed mitochondrial DNA datasets from 21 vertebrate and invertebrate species in southern California to identify areas with common phylogeographic breaks and high intrapopulation diversity. The result is an evolutionary framework for southern California within which patterns of genetic diversity can be analyzed in the context of historical processes, future evolutionary potential and current reserve design. Our multi-species genetic landscapes pinpoint six hotspots where interpopulation genetic divergence is consistently high, five evolutionary hotspots within which genetic connectivity is high, and three hotspots where intrapopulation genetic diversity is high. These 14 hotspots can be grouped into eight geographic areas, of which five largely are unprotected at this time. The multi-species genetic landscape approach may provide an avenue to readily incorporate measures of evolutionary process into GIS-based systematic conservation assessment and land-use planning.     

Effects of Road Deicer Runoff on Benthic Macroinvertebrate Communities in Korean Freshwaters with Toxicity Tests of Calcium Chloride (CaCl2)

Quantifying plant biomass and related processes such as element allocation is a major challenge at the scale of entire riparian zones. We applied sub-decimetre-resolution (5 cm) remote sensing using an unmanned aircraft system (UAS) in combination with field sampling to quantify riparian vegetation biomass at three locations (320-m river stretches) along a mining-impacted boreal river and estimated the amounts of Cd, Cu, and Zn stored in the dominant species. A species-level vegetation map was derived from visual interpretation of aerial images acquired using the UAS and field sampling to determine species composition and cover. Herbaceous and shrub biomass and metal contents were assessed by combining the vegetation maps with field sampling results. Riparian zone productivity decreased from 9.5 to 5.4 t ha^?1 with increasing distance from the source of contamination, and the total amount of vegetation-bound Cd and Zn decreased from 24 to 0.4 and 3,488 to 211 g, respectively. Most Cu was stored at the central location. Biomass and metal contents indicated large variation between species. Salix spp. comprised only 17 % of the total dominant-species biomass but contained 95 % of all Cd and 65 % of all Zn. In contrast, Carex rostrata/vesicaria comprised 64 % of the total dominant-species biomass and contained 63 % of all Cu and 25 % of all Zn. Our study demonstrates the applicability of UAS for monitoring entire riparian zones. The method offers great potential for accurately assessing nutrient and trace element cycling in the riparian zone and for planning potential phytoremediation measures in polluted areas.     

Short-term effects of thinning on soil respiration in a pine (Pinus tabulaeformis) plantation

Respiration was measured at daytime during the growing seasons (May–October) of 2011 and 2012 in a young Pinus tabulaeformis plantation with heavy, medium and light intensity thinning and unthinned control plots in Shanxi province in northern China. Soil temperature, moisture, fine root biomass, amounts of soil organic C and litterfall biomass were also measured. We found that immediately following thinning treatments, soil respiration increased by 8 %–21 % compared with the unthinned control plots during both growing seasons. Thinning significantly affected soil respiration and soil temperature with different thinning intensities, while there were no significant differences in soil moisture among the various treatments. During the growing seasons, the soil respiration rates were positively correlated with the soil moisture: the 19.4 %–54.0 % variation in soil respiration rates in the four thinning regimes are explained by the changes in soil moisture. Meanwhile, a positive correlation was found between soil temperature and soil respiration rates at all sites. The best fitting model with temperature and moisture explained 44.3 % of the variation in soil respiration in the high thinning treatment, 27.6 % in the light thinning treatment, 18.6 % in medium thinning and in the control sites during the measuring periods. Overall, soil respiration is better predicted by soil moisture, soil organic C, live fine root biomass and soil temperature when data are pooled for all thinning treatments over the two growing seasons. The best regression model explained 74.7 % of the total variation in soil respiration over the different thinning intensities for the two sampling periods.     

Spatial Regression Modeling for Compositional Data With Many Zeros

Compositional data analysis considers vectors of nonnegative-valued variables subject to a unit-sum constraint. Our interest lies in spatial compositional data, in particular, land use/land cover (LULC) data in the northeastern United States. Here, the observations are vectors providing the proportions of LULC types observed in each 3 km×3 km grid cell, yielding order 10⁴ cells. On the same grid cells, we have an additional compositional dataset supplying forest fragmentation proportions. Potentially useful and available covariates include elevation range, road length, population, median household income, and housing levels. We propose a spatial regression model that is also able to capture flexible dependence among the components of the observation vectors at each location as well as spatial dependence across the locations of the simplex-restricted measurements. A key issue is the high incidence of observed zero proportions for the LULC dataset, requiring incorporation of local point masses at 0. We build a hierarchical model prescribing a power scaling first stage and using latent variables at the second stage with spatial structure for these variables supplied through a multivariate CAR specification. Analyses for the LULC and forest fragmentation data illustrate the interpretation of the regression coefficients and the benefit of incorporating spatial smoothing.     

Measuring the rhizodeposition of carbon by rice: an approach based on carbon flux observations

ABSTRACT

Rhizodeposition is an important component of carbon cycling in terrestrial ecosystems. However, there remains tremendous uncertainty in its quantification due to the methodological limitations. In the present study, we propose a method to evaluate the rhizodeposition by plants by observing carbon flux. We investigated the ecosystem CO₂ flux variability and calculated the rhizodeposition of carbon by the rice rhizosphere, by using the carbon flux, meteorological data, and biomass observation from 2003 to 2011 at the Taoyuan Agro-ecological Experimental Station, a representative subtropical paddy ecosystem. Our data indicated that the process of rhizodeposition is the major reason for the discrepancy between the biomass and net primary productivity of the paddy ecosystem under intensive human interference. Both the amount and ratio of rhizodeposition of carbon in this paddy ecosystem were assessed; this provides important theoretical and methodological support for further investigating rhizodeposition by rice under field conditions. The rhizodeposition amount in the growing season of early rice, late rice, and for the entire planting period was 0.52–2.56, 0.74–3.75, and 1.61–5.24 t ha^?1, respectively, with the corresponding mean (±SD) rhizodeposition ratios of 23.16 ± 8.87%, 28.16 ± 12.94%, and 27.00 ± 9.3%. This method enabled us to calculate rhizodeposition under in situ conditions, and the results showed that the growing season of late rice was the primary period for rhizodeposition in rice ecosystem.     

Bayesian analysis of semiparametric linear-circular models

In many environmental and agricultural studies, data are collected on both linear and circular random variables, with possible dependence between the variables. Classically, the analysis of such data has been carried out in a classical regression framework. We propose a Bayesian hierarchical framework to handle all forms of uncertainty arising in a linear-circular data set. One novelty of our multivariate linear-circular model is that, marginally, the circular component is assumed to be a mixture model with an unknown number of von Mises (or circular normal) distributions. We use the Dirichlet process to introduce variability in the model dimensionality, and develop a simple Gibbs sampling algorithm for simulating the mixture components. Although we illustrate our methodology on von Mises mixtures, it is widely applicable. We thus avoid complicated reversible-jump Markov chain Monte Carlo methods, which are considered ideal for analyzing mixtures of unknown number of distributions. We illustrate our methodologies with simulated and real data sets. Using pseudo-Bayes factors, we also compare different models associated with both fixed and variable numbers of von Mises distributions. Our findings suggest that models associated with varying numbers of mixture components perform at least as well as those with known numbers of mixture components. We tentatively argue that model averaging associated with variable number of mixture components improves the model’s predictive power, which compensates for the lack of knowledge of the actual number of mixture components.     

Relationships of some environmental variables to the aggregation patterns of soil microarthropod populations in forests

Soil Collembola populations exhibit a non-random distribution pattern, which has been associated with a number of environmental variables. The purpose of this study is a) to investigate the patterns of aggregation and the relationship of the population density of selected soil Collembola species to environmental variables and b) to test whether numerical abundance and biomass as measures of population density lead to consistent results regarding these aspects of their ecology. A gradient of soil organic matter content and a gradient of soil pH, both occurring within limited space, were studied in two different sites. Taylor's b was used as an aggregation index. Two multiple regression models were estimated for each dominant species in each study site linking numerical abundance or biomass to environmental variables. The species studied exhibited different degrees of aggregation. These differences matched closely the differences in the strength of the association between population density and soil organic matter or pH, depending on the site. The regression models estimated for the biomass of species for which accurate methods of biomass estimation are available, exhibited a better fit than the models estimated for the numerical abundance of the same population.     

A Spatio-Temporal Downscaler for Output From Numerical Models

Often, in environmental data collection, data arise from two sources: numerical models and monitoring networks. The first source provides predictions at the level of grid cells, while the second source gives measurements at points. The first is characterized by full spatial coverage of the region of interest, high temporal resolution, no missing data but consequential calibration concerns. The second tends to be sparsely collected in space with coarser temporal resolution, often with missing data but, where recorded, provides, essentially, the true value. Accommodating the spatial misalignment between the two types of data is of fundamental importance for both improved predictions of exposure as well as for evaluation and calibration of the numerical model. In this article we propose a simple, fully model-based strategy to downscale the output from numerical models to point level. The static spatial model, specified within a Bayesian framework, regresses the observed data on the numerical model output using spatially-varying coefficients which are specified through a correlated spatial Gaussian process.     

Estimation of Fine Root Biomass of Alders Growing on Technosols Using Two Different Methods

Fine roots play an important role in organic matter accumulation in reclaimed mine soils. However, estimation of the increment of fine root biomass is difficult and none of the existing methods is universal. The paper examined two methods for measurement of fine roots biomass increment (FRBI): i) with using the root-ingrowth core method (RIC) and ii) the monolith sampling method (MSC). The study was conducted under alder plantings (Alnus incana, A. glutinosa and A. viridis) introduced on technosols at a combustion waste disposal site and a former open-cast sand mine. The FRBI determined using MSC method was significantly lower (33–481 g m^?2 yr^?1) and less variable than the FRBI measured with RIC (85–2317 g m^?2 yr^?1). However, the results obtained with both methods were correlated (r = 0.70, P = 0,05). Consequently, MSC is better to qualitatively compare the habitats of tree species in terms of their ability to produce fine roots. However, in the initial soils where plants very often produce more fine roots, RIC seems to be more suitable. This method shows the actual ability of trees to produce roots in order to satisfy their life needs when acquiring a new habitat on reclaimed soils. Such information is particularly important in oligotrophic soils where nutrient deficiency may be balanced only by the efficient circulation and decomposition of organic matter (SOM) including the fine roots that die off after each growing season.     

Multi-species occurrence models to evaluate the effects of conservation and management actions

Conservation and management actions often have direct and indirect effects on a wide range of species. As such, it is important to evaluate the impacts that such actions may have on both target and non-target species within a region. Understanding how species richness and composition differ as a result of management treatments can help determine potential ecological consequences. Yet it is difficult to estimate richness because traditional sampling approaches detect species at variable rates and some species are never observed. We present a framework for assessing management actions on biodiversity using a multi-species hierarchical model that estimates individual species occurrences, while accounting for imperfect detection of species. Our model incorporates species-specific responses to management treatments and local vegetation characteristics and a hierarchical component that links species at a community-level. This allows for comprehensive inferences on the whole community or on assemblages of interest. Compared to traditional species models, occurrence estimates are improved for all species, even for those that are rarely observed, resulting in more precise estimates of species richness (including species that were unobserved during sampling). We demonstrate the utility of this approach for conservation through an analysis comparing bird communities in two geographically similar study areas: one in which white-tailed deer (Odocoileus virginianus) densities have been regulated through hunting and one in which deer densities have gone unregulated. Although our results indicate that species and assemblage richness were similar in the two study areas, point-level richness was significantly influenced by local vegetation characteristics, a result that would have been underestimated had we not accounted for variability in species detection.     

Evaluation of the spatial pattern of surface soil water content of a karst hillslope in Southwest China using a state-space approach

This study aims to evaluate the effects of soil physicochemical properties and environmental factors on the spatial patterns of surface soil water content (SWC) based on the state-space approach and linear regression analysis. For this purpose, based on a grid sampling scheme (10 m × 10 m) applied to a 90 m × 120 m plot located on a karst hillslope of Southwest China, the SWC at 0–16 cm depth was measured 3 times across 130 sampling points, and soil texture, bulk density (BD), saturated hydraulic conductivity (K_s), organic carbon (SOC), and rock fragment content as well as site elevation (SE) were also measured at these locations. Results showed that the distribution pattern of SWC could be more successfully predicted by the first-order state-space models (R² = 67.5–99.9% and RMSE = 0.01–0.14) than the classic linear regression models (R² = 10.8–79.3% and RMSE = 0.11–0.24). The input combination containing silt content (Silt), K_s, and SOC produced the best state-space model, explaining 99.9% of the variation in SWC. And Silt was identified as the first-order controlling factor that explained 98.7% of the variation. In contrast, the best linear regression model using all of the variables only explained 79.3% of variation.     

Chemometric characterization of fruit juices from Spanish cultivars according to their phenolic compound contents: I. Citrus fruits

The data set composed by phenolic compound profiles of 83 Citrus juices (determined by HPLC-DAD-MS/MS) was evaluated by chemometrics to differentiate them according to Citrus species (sweet orange, tangerine, lemon, and grapefruit). Cluster analysis (CA) and principal component analysis (PCA) showed natural sample grouping among Citrus species and even the Citrus subclass. Most of the information contained in the full data set can be captured if only 15 phenolic compounds (concentration ≥10 mg/L), which can be quantified with fast and accurate methods in real samples, are introduced in the models; a good classification which allows the confirmation of the authenticity of juices is achieved by linear discriminant analysis. Using this reduced data set, fast and routine methods have been developed for predicting the percentage of grapefruit in adulterated sweet orange juices using principal component regression (PCR) and partial least-squares regression (PLS). The PLS model has provided suitable estimation errors.     

Application of an Adaptive Neural-Based Fuzzy Inference System Model for Predicting Leaf Area

Leaf Area (LA) is a key index of plant productivity and growth. A multiple linear regression technique is commonly applied to estimate LA as a non-destructive and quick method, but this technique is limited under the realistic situation. Thus, it is indispensable to elaborate new models for estimation. In this research, the performance of the Adaptive Neural-Based Fuzzy Inference System (ANFIS) in predicting the LA of 61 plant species (C) was investigated. Four parameters including leaf length (L), leaf width (W), C, and specific coefficient (K) for each plant were selected as input data to the ANFIS model and the LA as the output. Seven different ANFIS models including different combinations of input data were constructed to reveal the sensitivity analysis of the models. The normalized root mean square error (NRMSE), mean residual error (MRE), and linear regression were applied between observed LA and estimated LA by the models. The results indicated that ANFIS4-K_2min which employed all input data was the most accurate (NRMSE = 0.046 and R² = 0.997) and ANFIS1 which employed only the K input was the worst (NRMSE = 0.452 and R² = 0.778). In ranking, ANFIS4-K_2ave, ANFIS4-K_1min, ANFIS4-K_1ave, ANFIS3, and ANFIS2 ranked second, third, fourth, fifth, and sixth, respectively. The sensitivity analysis indicated that the predicted LA is more sensitive to the K, followed by L, W, and C. The results displayed that estimations are slightly overestimated. This study demonstrated that the ANFIS model could be accurate and faster alternative to the available laborious and time-consuming methods for LA prediction.