Land-Cover Classification Using MaxEnt: Can We Trust in Model Quality Metrics for Estimating Classification Accuracy?

MaxEnt is a popular maximum entropy-based algorithm originally developed for modelling species distribution, but increasingly used for land-cover classification. In this article, we used MaxEnt as a single-class land-cover classification and explored if recommended procedures for generating high-quality species distribution models also apply for generating high-accuracy land-cover classification. We used remote sensing imagery and randomly selected ground-true points for four types of land covers (built, grass, deciduous, evergreen) to generate 1980 classification maps using MaxEnt. We calculated different accuracy discrimination and quality model metrics to determine if these metrics were suitable proxies for estimating the accuracy of land-cover classification outcomes. Correlation analysis between model quality metrics showed consistent patterns for the relationships between metrics, but not for all land-covers. Relationship between model quality metrics and land-cover classification accuracy were land-cover-dependent. While for built cover there was no consistent patterns of correlations for any quality metrics; for grass, evergreen and deciduous, there was a consistent association between quality metrics and classification accuracy. We recommend evaluating the accuracy of land-cover classification results by using proper discrimination accuracy coefficients (e.g., Kappa, Overall Accuracy), and not placing all the confidence in model's quality metrics as a reliable indicator of land-cover classification results.

One-class land-cover classification using MaxEnt: the effect of modelling parameterization on classification accuracy.

Multiple-class land-cover classification approaches can be inefficient when the main goal is to classify only one or a few classes. Under this scenario one-class classification algorithms could be a more efficient alternative. Currently there are several algorithms that can fulfil this task, with MaxEnt being one of the most promising. However, there is scarce information regarding parametrization for performing land-cover classification using MaxEnt. In this study we aimed to understand how MaxEnt parameterization affects the classification accuracy of four different land-covers (i.e., built-up, irrigated grass, evergreen trees and deciduous trees) in the city of Santiago de Chile. We also evaluated if MaxEnt manual parameterization outperforms classification results obtained when using MaxEnt default parameters setting. To accomplish our objectives, we generated a set of 25,344 classification maps (i.e., 6,336 for each assessed land-cover), which are based on all the potential combination of 12 different classes of features restrictions, four regularization multipliers, four different sample sizes, three training/testing proportions, and 11 thresholds for generating the binary maps. Our results showed that with a good parameterization, MaxEnt can effectively classify different land covers with kappa values ranging from 0.68 for deciduous trees to 0.89 for irrigated grass. However, the accuracy of classification results is highly influenced by the type of land-cover being classified. Simpler models produced good classification outcomes for homogenous land-covers, but not for heterogeneous covers, where complex models provided better outcomes. In general, manual parameterization improves the accuracy of classification results, but this improvement will depend on the threshold used to generate the binary map. In fact, threshold selection showed to be the most relevant factor impacting the accuracy of the four land-cover classification. The number of sampling points for training the model also has a positive effect on classification results. However, this effect followed a logarithmic distribution, showing an improvement of kappa values when increasing the sampling from 40 to 60 points, but showing only a marginal effect if more than 60 sampling points are used. In light of these results, we suggest testing different parametrization and thresholds until satisfactory kappa or other accuracy metrics values are achieved. Our results highlight the huge potential that MaxEnt has a as a tool for one-class classification, but a good understanding of the software settings and model parameterization is needed to obtain reliable results.

MaxEnt's parameter configuration and small samples: are we paying attention to recommendations? A systematic review.

Environmental niche modeling (ENM) is commonly used to develop probabilistic maps of species distribution. Among available ENM techniques, MaxEnt has become one of the most popular tools for modeling species distribution, with hundreds of peer-reviewed articles published each year. MaxEnt's popularity is mainly due to the use of a graphical interface and automatic parameter configuration capabilities. However, recent studies have shown that using the default automatic configuration may not be always appropriate because it can produce non-optimal models; particularly when dealing with a small number of species presence points. Thus, the recommendation is to evaluate the best potential combination of parameters (feature classes and regularization multiplier) to select the most appropriate model. In this work we reviewed 244 articles published between 2013 and 2015 to assess whether researchers are following recommendations to avoid using the default parameter configuration when dealing with small sample sizes, or if they are using MaxEnt as a "black box tool." Our results show that in only 16% of analyzed articles authors evaluated best feature classes, in 6.9% evaluated best regularization multipliers, and in a meager 3.7% evaluated simultaneously both parameters before producing the definitive distribution model. We analyzed 20 articles to quantify the potential differences in resulting outputs when using software default parameters instead of the alternative best model. Results from our analysis reveal important differences between the use of default parameters and the best model approach, especially in the total area identified as suitable for the assessed species and the specific areas that are identified as suitable by both modelling approaches. These results are worrying, because publications are potentially reporting over-complex or over-simplistic models that can undermine the applicability of their results. Of particular importance are studies used to inform policy making. Therefore, researchers, practitioners, reviewers and editors need to be very judicious when dealing with MaxEnt, particularly when the modelling process is based on small sample sizes.

Nitric Oxide Synthase 1 Modulates Basal and ß-Adrenergic-Stimulated Contractility by Rapid and Reversible Redox-Dependent S-Nitrosylation of the Heart.

S-nitrosylation of several Ca2+ regulating proteins in response to ß-adrenergic stimulation was recently described in the heart; however the specific nitric oxide synthase (NOS) isoform and signaling pathways responsible for this modification have not been elucidated. NOS-1 activity increases inotropism, therefore, we tested whether ß-adrenergic stimulation induces NOS-1-dependent S-nitrosylation of total proteins, the ryanodine receptor (RyR2), SERCA2 and the L-Type Ca2+ channel (LTCC). In the isolated rat heart, isoproterenol (10 nM, 3-min) increased S-nitrosylation of total cardiac proteins (+46±14%) and RyR2 (+146±77%), without affecting S-nitrosylation of SERCA2 and LTCC. Selective NOS-1 blockade with S-methyl-L-thiocitrulline (SMTC) and Nω-propyl-l-arginine decreased basal contractility and relaxation (-25-30%) and basal S-nitrosylation of total proteins (-25-60%), RyR2, SERCA2 and LTCC (-60-75%). NOS-1 inhibition reduced (-25-40%) the inotropic response and protein S-nitrosylation induced by isoproterenol, particularly that of RyR2 (-85±7%). Tempol, a superoxide scavenger, mimicked the effects of NOS-1 inhibition on inotropism and protein S-nitrosylation; whereas selective NOS-3 inhibitor L-N5-(1-Iminoethyl)ornithine had no effect. Inhibition of NOS-1 did not affect phospholamban phosphorylation, but reduced its oligomerization. Attenuation of contractility was abolished by PKA blockade and unaffected by guanylate cyclase inhibition. Additionally, in isolated mouse cardiomyocytes, NOS-1 inhibition or removal reduced the Ca2+-transient amplitude and sarcomere shortening induced by isoproterenol or by direct PKA activation. We conclude that 1) normal cardiac performance requires basal NOS-1 activity and S-nitrosylation of the calcium-cycling machinery; 2) ß-adrenergic stimulation induces rapid and reversible NOS-1 dependent, PKA and ROS-dependent, S-nitrosylation of RyR2 and other proteins, accounting for about one third of its inotropic effect.

Differential role of S-nitrosylation and the NO-cGMP-PKG pathway in cardiac contractility.

The role of nitric oxide (NO) in cardiac contractility is complex and controversial. Several NO donors have been reported to cause positive or negative inotropism. NO can bind to guanylate cyclase, increasing cGMP production and activating PKG. NO may also directly S-nitrosylate cysteine residues of specific proteins. We used the isolated rat heart preparation to test the hypothesis that the differential inotropic effects depend on the degree of NO production and the signaling recruited. SNAP (S-nitroso-N-acetylpenicillamine), a NO donor, increased contractility at 0.1, 1 and 10 microM. This effect was independent of phospholamban phosphorylation, was not affected by PKA inhibition with H-89 (N-[2((p-bromocinnamyl)amino)ethyl]-5-isoquinolinesulfonamide), but it was abolished by the radical scavenger Tempol (4-hydroxy-[2,2,4,4]-tetramethyl-piperidine-1-oxyl). However, at 100 microM SNAP reduced contractility, effect reversed to positive inotropism by guanylyl cyclase blockade with ODQ (1H-[1,2,4]oxadiazolo[4,3-a]quinoxalin-1-one), and abolished by PKG inhibition with KT5823, but not affected by Tempol. SNAP increased tissue cGMP at 100 microM, but not at lower concentrations. Consistently, a cGMP analog also reduced cardiac contractility. Finally, SNAP at 1 microM increased the level of S-nitrosylation of various cardiac proteins, including the ryanodine receptor. This study demonstrates the biphasic role for NO in cardiac contractility in a given preparation; furthermore, the differential effect is clearly ascribed to the signaling pathways involved. We conclude that although NO is highly diffusible, its output determines the fate of the messenger: low NO concentrations activate redox processes (S-nitrosylation), increasing contractility; while the cGMP-PKG pathway is activated at high NO concentrations, reducing contractility.