Urban total ecological footprint forecasting by using radial basis function neural network: A case study of Wuhan city,China

Ecological footprint (EF) forecasting is essential for dynamically evaluating human impact on earth as well as for planning for a sustainable future. In this paper, a radial basis function neural network (RBFNN) model was developed to forecast the total ecological footprint (TEF) from 2006 to 2015. For a case study of Wuhan city, Hubei province in central China, per capita ecological footprint (EF) and biological capacity (BC) were calculated from 1988 to 2005. Partial least square (PLS) was used to select the important impact factors. We put the selected socio-economic factors as input and the TEF as output together to build RBFNN model and predict the development trends of the TEF in the following 10 years. Five-fold cross-validation was conducted to validate the model in the process of input selection and RBFNN model training. From the results, continuous increase of per capita EF (1988–2005) indicated stronger and stronger human effect on the district and Wuhan's ecological state is in the ecological deficit. Up to 2015, the district would have been bearing accumulative TEF of 24.782 million gha, which is near 2.5 times of that in 1988. Although the increase rate of gross domestic product (GDP) would be restricted in a lower level from 2006 to 2015, the urban ecological environmental burden could only respond to the socio-economic circumstances moderately.     

Assessment of the potential iridology for diagnosing kidney disease using wavelet analysis and neural networks

Alternative or complementary medicine emphasizes therapies that are claimed to improve quality of life, prevent disease, and address conditions that conventional medicine has limited success in curing. There are many techniques which are prevalent in many countries and these can cause harm if not scientifically evaluated. The objective of this paper is to validate the use of iridology to diagnose kidney abnormalities. Two subject groups were evaluated: one was 168 subjects free from kidney disease and the other was 172 subjects with chronic renal failure. The procedure to acquire, process and classify the iris images was designed in such a way that avoids any dependency on the iridologists by using wavelet analysis and Adaptive Neuro-Fuzzy Inference System. The results show a correct classification for both subjects with kidney problems and normal subjects of 82% and 93%, respectively. The proposed technique conducted on a systemic disease with ocular manifestations showed encouraging results. However, it is necessary to perform extensive studies with diseases that do not have ocular manifestations according to conventional medicine in order to validate iridology as a valid scientific technique.     

Systems biology beyond degree, hubs and scale-free networks: the case for multiple metrics in complex networks

Modeling and topological analysis of networks in biological and other complex systems, must venture beyond the limited consideration of very few network metrics like degree, betweenness or assortativity. A proper identification of informative and redundant entities from many different metrics, using recently demonstrated techniques, is essential. A holistic comparison of networks and growth models is best achieved only with the use of such methods.     

Time series forecasting model for fisheries in Chilika lagoon (a Ramsar site, 1981), Odisha,India: a case study

Chilika, a Ramsar site and the largest brackish water lagoon in Asia, is situated in East Coast of India, endowed with rich fisheries resources. In this study, SARIMAX fisheries forecasting model was developed by using seasonal ARIMA (Auto Regressive Integrated Moving Average) model with three external physicochemical factors (factor 1 was dominated by the combined effect of salinity and temperature and factor 2 and factor 3 were dominated by alkalinity and transparency) in Chilika. Monthly fish catch data and physico-chemical parameters of water from 2001–2002 to 2015–2016 was used to develop model. The results showed SARIMAX model; SARIMA (1,0,0)(2,0,0)₁₂ with factor 1, factor 2 and factor 3 was the best fitted model for the fish catch in Chilika. The factor 1 was found to be positive influence on catch at 10% level of significance (p = 0.089) while, factor 2 and factor 3 were found to be insignificant. The developed SARIMAX model was validated with actual annual fish catch for the years 2011–2015 with prediction error 3–7%. Further, the developed SARIMAX model was used to forecast fish catch for the period April 2016 to March 2018 indicating increasing 10% present catch in the lagoon. The developed SARIMAX model in the present case study is of the first time to forecast and visualise the positive influence of salinity and temperature on the fish catch in the Chilika lagoon.     

Evaluation using multilayer perception neural networks: a case study of undulatory median fin swimming in the knifefish Xenomystus nigri

In this study, artificial intelligence, namely multilayer perception neural networks (MLP-NN), was employed to predict the hydrodynamic performance of undulatory median fin propulsion in Xenomystus nigri . Good agreement was found between MLP-NN predictions and actual mean thrust and power values calculated from elongated-body theory. MLP-NN has the ability to be a predictive tool for autonomous underwater vehicle design and hydrodynamic performance.     

Spatial patterns of phylogenetic diversity and endemism in the Western Ghats,India: A case study using ancient predatory arthropods

The Western Ghats (WG) mountain chain in peninsular India is a global biodiversity hotspot, one in which patterns of phylogenetic diversity and endemism remain to be documented across taxa. We used a well‐characterized community of ancient soil predatory arthropods from the WG to understand diversity gradients, identify hotspots of endemism and conservation importance, and highlight poorly studied areas with unique biodiversity. We compiled an occurrence dataset for 19 species of scolopendrid centipedes, which was used to predict areas of habitat suitability using bioclimatic and geomorphological variables in Maxent. We used predicted distributions and a time‐calibrated species phylogeny to calculate taxonomic and phylogenetic indices of diversity, endemism, and turnover. We observed a decreasing latitudinal gradient in taxonomic and phylogenetic diversity in the WG, which supports expectations from the latitudinal diversity gradient. The southern WG had the highest phylogenetic diversity and endemism, and was represented by lineages with long branch lengths as observed from relative phylogenetic diversity/endemism. These results indicate the persistence of lineages over evolutionary time in the southern WG and are consistent with predictions from the southern WG refuge hypothesis. The northern WG, despite having low phylogenetic diversity, had high values of phylogenetic endemism represented by distinct lineages as inferred from relative phylogenetic endemism. The distinct endemic lineages in this subregion might be adapted to life in lateritic plateaus characterized by poor soil conditions and high seasonality. Sites across an important biogeographic break, the Palghat Gap, broadly grouped separately in comparisons of species turnover along the WG. The southern WG and Nilgiris, adjoining the Palghat Gap, harbor unique centipede communities, where the causal role of climate or dispersal barriers in shaping diversity remains to be investigated. Our results highlight the need to use phylogeny and distribution data while assessing diversity and endemism patterns in the WG.     

A geospatial approach to monitoring impervious surfaces in watersheds using Landsat data (the Mondego Basin,Portugal as a case study)

The urbanization of watersheds is a highly dynamic global phenomenon that must be monitored. With consequences for the environment, the population, and the economy, accurate products at adequate spatial and temporal resolutions are required and demanded by the science community and stakeholders alike. To address these needs, a new Impervious Surface Area (ISA) product was created for a Portuguese Watershed (Mondego river) from Landsat data (a combination of leaf-on multispectral bands, derived products, and NDVI time series), using Regression Tree Models (RTM). The product provides 30-m spatial resolution ISA estimates (0–100%) with a Mean Average Error (MAE) of 1.6% and Root Mean Square Error (RMSE) of 5.5%.A strategy to update the baseline product was tested in earlier imagery (2001 and 2007) for a subset of the watershed. Instead of updating the baseline product, the strategy seeks to identify stable training samples and remove those where change was detected in a time series of Change Vector Analysis (CVA). The stable samples were then used to create new ISA models using RTM. The updated maps were similar to the original product in terms of accuracy metrics (MAE: 2001: 2.6%; 2007:3.6%).The products and methodology offer a new perspective on the urban development of the watershed, at a scale previously unavailable. It can also be replicated elsewhere at a low cost, leveraging the growing Landsat data archive, and provide timely information on relevant land cover metrics to the scientific community and stakeholders.     

Description of a new species of the genus Awaous Valenciennes, 1837 (Gobiiformes: Oxudercidae) from the middle stretch of the Mahanadi River,Odisha, India,with comments on the Awaous species from India

A new species of the genus Awaous (Oxudercidae), Awaous motla sp. nov., is described based on 18 specimens collected from the Mahanadi River near Sonepur, Subarnapur District, and 3 specimens from the same river near Boudh bridge, Boudh District of Odisha, India. This species is distinct from its congeners by having a combination of characteristics: relatively small eyes, diameter of 6.6–8.4 in head length (LH); robust and long snout, 2.0–2.6 in LH; eye diameter 2.7–4.1 in snout length; cephalic sensory pore system interrupted with eight pores; predorsal scales 13–15; longitudinal scale series 55–58; gill rakers 2 + 1 + (6–7) on the first gill arch; teeth small, conical, and in a single row on the upper jaw and multiserial (2–3) on the lower jaw. This species is also differentiated from some of its congeners in the nucleotide composition of the cytochrome c oxidase I gene by 8.3%–13.8% Kimura two-parameter (K2P) distance and belongs to a separate cluster in the maximum likelihood tree analysis. This finding is also supported by the species delimitation analysis based on Assemble Species by Automatic Partitioning. The new species holds high commercial value in its locality and needs special conservation attention for sustainable utilization.     

Using learning networks to understand complex systems: a case study of biological,geophysical and social research in the Amazon

Developing high‐quality scientific research will be most effective if research communities with diverse skills and interests are able to share information and knowledge, are aware of the major challenges across disciplines, and can exploit economies of scale to provide robust answers and better inform policy. We evaluate opportunities and challenges facing the development of a more interactive research environment by developing an interdisciplinary synthesis of research on a single geographic region. We focus on the Amazon as it is of enormous regional and global environmental importance and faces a highly uncertain future. To take stock of existing knowledge and provide a framework for analysis we present a set of mini‐reviews from fourteen different areas of research, encompassing taxonomy, biodiversity, biogeography, vegetation dynamics, landscape ecology, earth‐atmosphere interactions, ecosystem processes, fire, deforestation dynamics, hydrology, hunting, conservation planning, livelihoods, and payments for ecosystem services. Each review highlights the current state of knowledge and identifies research priorities, including major challenges and opportunities. We show that while substantial progress is being made across many areas of scientific research, our understanding of specific issues is often dependent on knowledge from other disciplines. Accelerating the acquisition of reliable and contextualized knowledge about the fate of complex pristine and modified ecosystems is partly dependent on our ability to exploit economies of scale in shared resources and technical expertise, recognise and make explicit interconnections and feedbacks among sub‐disciplines, increase the temporal and spatial scale of existing studies, and improve the dissemination of scientific findings to policy makers and society at large. Enhancing interaction among research efforts is vital if we are to make the most of limited funds and overcome the challenges posed by addressing large‐scale interdisciplinary questions. Bringing together a diverse scientific community with a single geographic focus can help increase awareness of research questions both within and among disciplines, and reveal the opportunities that may exist for advancing acquisition of reliable knowledge. This approach could be useful for a variety of globally important scientific questions.     

Probabilistic seasonal dengue forecasting in Vietnam: A modelling study using superensembles

BackgroundWith enough advanced notice, dengue outbreaks can be mitigated. As a climate-sensitive disease, environmental conditions and past patterns of dengue can be used to make predictions about future outbreak risk. These predictions improve public health planning and decision-making to ultimately reduce the burden of disease. Past approaches to dengue forecasting have used seasonal climate forecasts, but the predictive ability of a system using different lead times in a year-round prediction system has been seldom explored. Moreover, the transition from theoretical to operational systems integrated with disease control activities is rare.Methods and findingsWe introduce an operational seasonal dengue forecasting system for Vietnam where Earth observations, seasonal climate forecasts, and lagged dengue cases are used to drive a superensemble of probabilistic dengue models to predict dengue risk up to 6 months ahead. Bayesian spatiotemporal models were fit to 19 years (2002–2020) of dengue data at the province level across Vietnam. A superensemble of these models then makes probabilistic predictions of dengue incidence at various future time points aligned with key Vietnamese decision and planning deadlines. We demonstrate that the superensemble generates more accurate predictions of dengue incidence than the individual models it incorporates across a suite of time horizons and transmission settings. Using historical data, the superensemble made slightly more accurate predictions (continuous rank probability score [CRPS] = 66.8, 95% CI 60.6–148.0) than a baseline model which forecasts the same incidence rate every month (CRPS = 79.4, 95% CI 78.5–80.5) at lead times of 1 to 3 months, albeit with larger uncertainty. The outbreak detection capability of the superensemble was considerably larger (69%) than that of the baseline model (54.5%). Predictions were most accurate in southern Vietnam, an area that experiences semi-regular seasonal dengue transmission. The system also demonstrated added value across multiple areas compared to previous practice of not using a forecast. We use the system to make a prospective prediction for dengue incidence in Vietnam for the period May to October 2020. Prospective predictions made with the superensemble were slightly more accurate (CRPS = 110, 95% CI 102–575) than those made with the baseline model (CRPS = 125, 95% CI 120–168) but had larger uncertainty. Finally, we propose a framework for the evaluation of probabilistic predictions. Despite the demonstrated value of our forecasting system, the approach is limited by the consistency of the dengue case data, as well as the lack of publicly available, continuous, and long-term data sets on mosquito control efforts and serotype-specific case data.ConclusionsThis study shows that by combining detailed Earth observation data, seasonal climate forecasts, and state-of-the-art models, dengue outbreaks can be predicted across a broad range of settings, with enough lead time to meaningfully inform dengue control. While our system omits some important variables not currently available at a subnational scale, the majority of past outbreaks could be predicted up to 3 months ahead. Over the next 2 years, the system will be prospectively evaluated and, if successful, potentially extended to other areas and other climate-sensitive disease systems.     

Effects of chameleon dispense-to-plunge speed on particle concentration,complex formation,and final resolution: A case study using the Neisseria gonorrhoeae ribonucleotide reductase inactive complex

Ribonucleotide reductase (RNR) is an essential enzyme that converts ribonucleotides to deoxyribonucleotides and is a promising antibiotic target, but few RNRs have been structurally characterized. We present the use of the chameleon, a commercially-available piezoelectric cryogenic electron microscopy plunger, to address complex denaturation in the Neisseria gonorrhoeae class Ia RNR. Here, we characterize the extent of denaturation of the ring-shaped complex following grid preparation using a traditional plunger and using a chameleon with varying dispense-to-plunge times. We also characterize how dispense-to-plunge time influences the amount of protein sample required for grid preparation and preferred orientation of the sample. We demonstrate that the fastest dispense-to-plunge time of 54 ms is sufficient for generation of a data set that produces a high quality structure, and that a traditional plunging technique or slow chameleon dispense-to-plunge times generate data sets limited in resolution by complex denaturation. The 4.3 Å resolution structure of Neisseria gonorrhoeae class Ia RNR in the inactive α4β4 oligomeric state solved using the chameleon with a fast dispense-to-plunge time yields molecular information regarding similarities and differences to the well studied Escherichia coli class Ia RNR α4β4 ring.     

Short- and long-term diets of the threatened longhorned pygmy devil ray,Mobula eregoodoo determined using stable isotopes

Most mobulids are listed as near threatened to endangered. Nonetheless, effective conservation measures are hindered by knowledge gaps in their ecology and behaviour. In particular, few studies have assessed diets and trophic ecologies that could inform methods to avoid fishing mortality. Here, a shortfall in data for the longhorned pygmy devil ray, Mobula eregoodoo was addressed by describing temporal variability in dietary preferences using stable isotope analysis. During summer and autumn in 2017, five bather-protection gillnets were deployed off eastern Australia (29° S, 153.5° E). From the catches of these gillnets, 35 adult M. eregoodoo had liver, muscle and stomach contents sampled to determine δ¹³C and δ¹⁵N profiles. Analyses revealed that surface zooplankton and zooplanktivorous teleosts were important dietary components across short- and long-term temporal scales. Large quantities of undigested sandy sprat, Hyperlophus vittatus, in the stomachs of some specimens unequivocally confirm feeding on teleosts. A narrow isotopic niche and minimal isotopic overlap with reef manta rays, Mobula alfredi from the same geographic region in eastern Australia implies M. eregoodoo has unique and highly specialised resource use relative to other mobulids in the area. The species is clearly vulnerable to capture during inshore migrations, presumably where they feed on shallow-water shoaling teleosts. Female M. eregoodoo likely have a low annual reproductive output, so population recoveries from fishing-induced declines are likely to be slow. Measures to reduce the by catch of M. eregoodoo in local bather-protection gillnets, and artisanal fisheries more broadly, should be given priority.     

Application of neural networks using the volume learning algorithm for the study of structure-activity relationship in chemical compounds

A volume learning algorithm for artificial neural networks was developed to quantitatively describe the three-dimensional structure-activity relationships using as an example N-benzylpiperidine derivatives. The new algorithm combines two types of neural networks, the Kohonen and the feed-forward artificial neural networks, which are used to analyze the input grid data generated by the comparative molecular field approach. Selection of the most informative parameters using the algorithm helped to reveal the most important spatial properties of the molecules, which affect their biological activities. Cluster regions determined using the new algorithm adequately predicted the activity of molecules from a control data set.     

A comparative study of electronic and neural networks involved in pattern recognition

The comparative study of electronic and neural networks involved in pattern recognition starts with the analogies of structure and function which exist between the electronic “basic integrative unit” and the neuron. Both elements represent the basic components in each system of networks and may be considered as functionally equivalent.According to the kind of response given to a standard input signal, four types of integrative units, either electronic or neural, may be distinguished: the fixed, the accommodative, the signal prolongating and the adaptive type.The integrative units perform many different functions. Those involved in pattern recognition, however, can all be grouped into three categories according to one of the following functions they perform: contrast detection, pattern detection and pattern discrimination. A “contrast detecting unit” gives responses in two senses, positive or negative, according to the position of the stimulus over its receptive field. A “pattern detecting unit” gives responses in one sense only, with a maximum for a pattern having the spatial distribution corresponding to the positive acting receptors of its receptive field. For performing the function of discrimination, which leads to reliable identification of any pattern, a network arrangement called a “maximum amplitude filter” is necessary. Examples of such units and arrangements existing in the nervous system are provided.It is concluded that a “logical analysis of neural networks” based on engineering principles is possible and that this could provide a new tool to the neurophysiologist in the study of the nervous system.     

A comparative study of multilayer perceptron neural networks for the identification of rhubarb samples

Artificial neural networks have gained much attention in recent years as fast and flexible methods for quality control in traditional medicine. Near-infrared (NIR) spectroscopy has become an accepted method for the qualitative and quantitative analyses of traditional Chinese medicine since it is simple, rapid, and non-destructive. The present paper describes a method by which to discriminate official and unofficial rhubarb samples using three layer perceptron neural networks applied to NIR data. Multilayer perceptron neural networks were trained with back propagation, delta-bar-delta and quick propagation algorithms. Results obtained using these methods were all satisfactory, but the best outcomes were obtained with the delta-bar-delta algorithm.     

The use of neural networks to aid in microorganism identification: a case study ofHaemophilus species identification

The adipamidase of a mutant strainBrevibacterium sp. R312 involved in the degradation of adiponitrile to adipic acid was purified. Its N-terminal amino acid sequence was shown to be identical toBrevibacterium sp. R312 enantio-selective amidase andRhodococcus sp. N-774 amidase.