Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
1,773
datasets available to search
ShareScore release 0.7.1
Dataset results
1,773 results for “predictive modeling”
FIGURE 12 in A fossil locality predictive model using weighted suitability analysis for the Early Cretaceous Cedar Mountain Formation, Utah, USA
FIGURE 12. Comparison of slopes between the entire Cedar Mountain Formation and BYU fossil localities.
FIGURE 8 in A fossil locality predictive model using weighted suitability analysis for the Early Cretaceous Cedar Mountain Formation, Utah, USA
FIGURE 8. Number of cells assigned to each fossil potential value for the model. TABLE 6. Reclassified values for OLI/TIRS bands for revised model.
FIGURE 5 in A fossil locality predictive model using weighted suitability analysis for the Early Cretaceous Cedar Mountain Formation, Utah, USA
FIGURE 5. Differences of means between fossil localities and Cedar Mountain Formation (X1-X2). TABLE 3. Reclassified values for OLI/TIRS bands used in weighted suitability analysis.
FIGURE 1 in A fossil locality predictive model using weighted suitability analysis for the Early Cretaceous Cedar Mountain Formation, Utah, USA
FIGURE 1. Early Cretaceous Cedar Mountain Formation surface exposure, elevation, and fossil localities.
FIGURE 11 in A fossil locality predictive model using weighted suitability analysis for the Early Cretaceous Cedar Mountain Formation, Utah, USA
FIGURE 11. Comparison of aspects between the entire Cedar Mountain Formation and BYU fossil localities.
Figure 3 in How can global climate change influence the geographic distribution of the eucalyptus yellow beetle? Modeling and prediction for Brazil
Figure 3. Predicting of potential areas to the occurrence of Costalimaita ferruginea in the period of 2061-2080, in two climate change scenarios, Representative Concentration Pathways (RCP) 4.5 e 8.5 (W/m2), using the algorithm Envelope Score (AUC = 0.808). The numbers 1 to 5 represent the Brazilian biomes, being 1 = Amazônia, 2 = Caatinga, 3 = Cerrado, 4 = Pantanal, 5 = Mata Atlântica e 6 = Pampa.
Figure 2 in How can global climate change influence the geographic distribution of the eucalyptus yellow beetle? Modeling and prediction for Brazil
Figure 2. Predicting of potential areas to the occurrence of Costalimaita ferruginea in the period of 2041-2060, in two climate change scenarios, Representative Concentration Pathways (RCP) 4.5 e 8.5 (W/m2), using the algorithm Envelope Score (AUC = 0.808). The numbers 1 to 5 represent the Brazilian biomes, being 1 = Amazônia, 2 = Caatinga, 3 = Cerrado, 4 = Pantanal, 5 = Mata Atlântica e 6 = Pampa.
Data from: Integrating genomic data and simulations to evaluate alternative species distribution models and improve predictions of glacial refugia and future responses to climate change
<p>Climate change poses a threat to biodiversity, and it is unclear whether species can adapt to or tolerate new conditions, or migrate to areas with suitable habitats. Reconstructions of range shifts that occurred in response to environmental changes since the last glacial maximum from species distribution models (SDMs) can provide useful data to inform conservation efforts. However, different SDM algorithms and climate reconstructions often produce contrasting patterns, and validation methods typically focus on accuracy in recreating current distributions, limiting their relevance for assessing predictions to the past or future. We modeled historically suitable habitat for the threatened North American tree green ash (<em>Fraxinus pennsylvanica</em>) using 24 SDMs built using two climate models, three calibration regions, and four modeling algorithms. We evaluated the SDMs using contemporary data with spatial block cross-validation and compared the relative support for alternative models using a novel integrative method based on coupled demographic-genetic simulations. We simulated genomic datasets using habitat suitability of each of the 24 SDMs in a spatially-explicit model. Approximate Bayesian Computation (ABC) was then used to evaluate the support for alternative SDMs through comparisons to an empirical population genomic dataset. Models had very similar performance when assessed with contemporary occurrences using spatial cross-validation, but ABC model selection analyses consistently supported SDMs based on the CCSM climate model, an intermediate calibration extent, and the generalized linear modeling algorithm. Finally, we projected the future range of green ash under four climate change scenarios. Future projections using the SDMs selected via ABC suggest only minor shifts in suitable habitat for this species, while some of those that were rejected predicted dramatic changes. Our results highlight the different inferences that may result from the application of alternative distribution modeling algorithms and provide a novel approach for selecting among a set of competing SDMs with independent data.</p>
Figure 5 in Development of predictive models for determining fetal age-at-length in belugas (Delphinapterus leucas) and their application toward in situ and ex situ population management
Figure 5. Illustration of the linear relationships between fetal age and growth measurements of biparietal diameter (BPD: top graph), thoracic diameter (TD: middle graph) and thoracic circumference (TC: bottom graph) in belugas.
Figure 4 in Development of predictive models for determining fetal age-at-length in belugas (Delphinapterus leucas) and their application toward in situ and ex situ population management
Figure 4. Comparisons of regression curves of TL growth during the first (●) and second half (○) of gestation (top graph) and the early (●), mid (○) and late (▲) pregnancy (bottom graph). The slopes of the regression lines for first half of gestation (F = 63.31, P <0.0001, df1 = 1, df2 = 33) and for early (F = 50.05, P <0.0001, df1 = 1, df2 = 37) and mid pregnancy (F = 135.04, P <0.0001, df1 = 1, df2 = 32) were different than those for the second half of gestation and late pregnancy, respectively. Note that the animals double in length during late pregnancy (315–473 d).
Figure 3 in Development of predictive models for determining fetal age-at-length in belugas (Delphinapterus leucas) and their application toward in situ and ex situ population management
Figure 3. Individual growth rate data from three animals (Animal 1, 2, 3). Regression line slopes during the first two-thirds of pregnancy (top graph) were similar (F = 0.48, P = 0.62, df1 = 2, df2 =18), while regression slopes where different (F = 15.13, P = 0.03, df1 = 2, df2 =3) from the second half to term. Animal 1 (▲) did not have any TL data beyond the first half of gestation so TL length data were used from the farthest in gestation and then again at term. Note that while growth rates were similar during the first two-thirds of pregnancy, fetuses were already different in size when initially detected.
Figure 2 in Development of predictive models for determining fetal age-at-length in belugas (Delphinapterus leucas) and their application toward in situ and ex situ population management
Figure 2. Fetal growth curve comparison illustrating different growth rates resulting in wide range in estimated gestation length as compared to known gestation length determined in this study. Data from Heide-Jørgensen and Teilmann (1994; dotted line) predicts a gestation length of 310 d for a 150 cm calf and similar to our study used a 2nd order polynomial regression to describe their data. Kleinenberg et al. ([1964] 1969: dashed line) developed a curve of the average monthly embryo/fetal growth. They did not provide the curve, only the predicted age at TL, which we then used to fit to a growth curve, which predicts 150 cm calf as 338 d.
Figure 1 in Development of predictive models for determining fetal age-at-length in belugas (Delphinapterus leucas) and their application toward in situ and ex situ population management
Figure 1. Ultrasonographic images of beluga fetuses. All images have yellow caliper lines used to measure dimensions. Biparietal diameter (A, B) at two different stages of gestation show the ovoid shaped skull and echo produced from falx (arrows) located midline between the parietal bones (arrowheads). The thoracic diameter (C) as measured between the yellow caliper marks (arrowheads) on the lateral side of the fetal thorax (d1 = 6.66 cm) at the level of the heart (white arrow) and thoracic circumference (c = 24.04 cm) determined by using the elliptical measurement caliper function to include the dorsal to ventral diameter (d2 = 8.67 cm). The total length of a fetus (D) which is bent in utero, thus requiring the addition of two separate measurements (arrowheads), 1) 8.38 cm from the cranial most aspect of the skull to mid abdomen and 2) 6.91 cm from mid abdomen to distal most portion of the peduncle for a total length of 15.29 cm.
Fig. 1 in Testing the robustness of transmission network models to predict ectoparasite loads. One lizard, two ticks and four years
Fig. 1. Transmission networks generated with (a) a short time window of infection; and (b) a long time window of infection, from the GPS location data of the lizards in the study population in 2010. Nodes represent individual lizards and edges between nodes are directed towards the lizard that is at risk of infection. The edges are weighted as described in the main text and the thicker the line the more weight is associated with that edge.
Supplementary material for publication "Multi-Echelon Inventory Optimization in Supply Chain Networks: Exploring Network Structures and Predictive Modeling"
<div> <div> <div> <p>This dataset collects different supply chain network structures generated artificially. We present four types of networks: Serial, Convergent, Divergent, and General, each type consisting of 20,000 individual instances. All 80,000 network instances generated are available to researchers and practitioners in Excel. The repository consists of separate files for each network instance consisting of each network inventory data, node connections, and a visual representation.</p> </div> </div> </div>
Figure 5. Sensory score and period of storage for processed cheese-Time-Delay Artificial Neural Network Computing Models for Predicting Shelf Life of Processed Cheese
<p>R2 was found to be 96.5 percent of the total variation as explained by sensory scores. Period<br> of storage (days) for which the processed cheese has been in the shelf can be determined based on<br> sensory score (Fig. 5).</p>
Figure 4. Comparison of ASS and PSS for multilayer model R-Time-Delay Artificial Neural Network Computing Models for Predicting Shelf Life of Processed Cheese
<p>TDNN models with single and multi layers were developed taking soluble nitrogen, pH,<br> standard plate count, yeast & mould count, spore count as input parameters, and sensory score as<br> output parameter for predicting the shelf life of processed cheese stored at 30o C. Mean Square<br> Error, Root Mean Square Error, Coefficient of Determination and Nash - Sutcliffo Coefficient were<br> used in order to compare the prediction ability of the developed TDNN models. Regression<br> equations were developed for predicting the shelf life of processed cheese, which came out as 28.25<br> days. Since, predicted value is close to the experimentally determined shelf life of 30 days, hence<br> from the study it can be concluded that TDNN artificial neural network models are quite efficient in<br> predicting shelf life of processed cheese.</p>
Figure 2. Training pattern of TDNN models-Time-Delay Artificial Neural Network Computing Models for Predicting Shelf Life of Processed Cheese
<p>The Neural Network Toolbox under MATLAB software was used for developing the TDNN<br> models. Training pattern of TDNN models is presented in Fig.2.</p>
Figure 1. Inputs and output parameters for TDNN models-Time-Delay Artificial Neural Network Computing Models for Predicting Shelf Life of Processed Cheese
<p>The data consisted of 36 samples, which were divided into two subsets, i.e., 30 used for<br> training the network and 6 for testing the TDNN models. Soluble nitrogen, pH, standard plate<br> count, yeast & mould count, and spore count were taken as input parameters, and sensory score as<br> output parameter for developing TDNN single and multilayer models (Fig.1).</p>
Figure 3. Comparison of ASS and PSS single layer model-Time-Delay Artificial Neural Network Computing Models for Predicting Shelf Life of Processed Cheese
<p>TDNN models with single and multi layers were developed taking soluble nitrogen, pH,<br> standard plate count, yeast & mould count, spore count as input parameters, and sensory score as<br> output parameter for predicting the shelf life of processed cheese stored at 30o C. Mean Square<br> Error, Root Mean Square Error, Coefficient of Determination and Nash - Sutcliffo Coefficient were<br> used in order to compare the prediction ability of the developed TDNN models. Regression<br> equations were developed for predicting the shelf life of processed cheese, which came out as 28.25<br> days. Since, predicted value is close to the experimentally determined shelf life of 30 days, hence<br> from the study it can be concluded that TDNN artificial neural network models are quite efficient in<br> predicting shelf life of processed cheese.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.