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.
13,064
datasets available to search
ShareScore release 0.9.0
Dataset results
13,064 results for “Prediction”
Sevilleta plant phenology predicts stability of primary production from 2002 to 2020.
The temporal stability of plant productivity affects species’ access to resources, exposure to stressors, and strength of interactions with other species in the community, including support to the food web. The magnitude of temporal stability may depend on how a species allocates resources across phenological stages, such as vegetative growth versus reproduction. Understanding whether and how plant phenological traits correlate with the long-term stability of plant biomass is particularly important in highly variable environments, such as drylands. We evaluated whether phenological traits predict the temporal stability of plant species productivity by correlating 18 years of monthly phenology observations with biannual estimates of aboveground plant biomass for 98 plant species from semi-arid grasslands and shrublands. We then paired these phenological traits with potential climate drivers to identify abiotic contexts that favor specific phenological strategies among plant species. Phenological traits strongly predicted the stability of plant species biomass. Plant species with longer annual vegetative phenophases had more stable production over time but also failed to fruit in a greater proportion of years, indicating a growth-reproduction trade-off. Earlier leaf- out dates, longer fruiting duration, and longer time lags between leaf and fruit production also predicted greater temporal stability. Species with stability-promoting traits began growing in drier conditions than their counterparts and experienced greater exposure to stress, evaluated by the wider range of temperatures and precipitation during biologically active periods. Our results suggest that bet-hedging strategies which spread resource acquisition and reproduction over longer time periods help to stabilize plant species productivity in variable environments.
Hippocampal-neocortical interactions sharpen over time for predictive actions
Open the record for dataset details and reuse information.
Data to "Predicting precision grip grasp locations on three-dimensional objects"
<p>This record contains experimental and analysis scripts (written in Matlab) as well as raw and processed data to reproduce the results shown in:</p> <p>Klein, L. K. ^, Maiello, G. ^, Paulun, V. C., & Fleming, R. W. (in press). <br> Predicting precision grip grasp locations on three-dimensional objects. PLOS Computational Biology<br> ^co-first authors </p> <p>A preprint version of the manuscript is currently available at: https://doi.org/10.1101/476176</p>
iSDAsoil: soil clay content (USDA system) for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil clay content (USDA system) in % predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, <a href="https://landpotential.org/data-portal/">LandPKS</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_clay_tot_psa_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil clay content mean value,</li> <li>sol_clay_tot_psa_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil clay content (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: clay_tot_psa R-square: 0.746 Fitted values sd: 16.5 RMSE: 9.63 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -75.803 -4.512 -0.178 3.748 82.146 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 4.494652 8.914671 0.504 0.61413 regr.ranger 1.076957 0.003611 298.210 < 2e-16 *** regr.xgboost -0.012617 0.004678 -2.697 0.00699 ** regr.cubist 0.030730 0.003930 7.820 5.32e-15 *** regr.nnet -0.238376 0.365390 -0.652 0.51415 regr.cvglmnet -0.044547 0.004379 -10.174 < 2e-16 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 9.629 on 122269 degrees of freedom Multiple R-squared: 0.7458, Adjusted R-squared: 0.7458 F-statistic: 7.175e+04 on 5 and 122269 DF, p-value: < 2.2e-16</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
iSDAsoil: soil extractable Iron for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil extractable Iron (Fe) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_log.fe_mehlich3_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Iron mean value,</li> <li>sol_log.fe_mehlich3_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Iron model (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: log.fe_mehlich3 R-square: 0.817 Fitted values sd: 0.497 RMSE: 0.235 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -4.0165 -0.1312 -0.0082 0.1238 2.5077 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 3.913522 1.869721 2.093 0.036344 * regr.ranger 0.856893 0.007912 108.306 < 2e-16 *** regr.xgboost 0.027856 0.007738 3.600 0.000318 *** regr.cubist 0.146095 0.007230 20.207 < 2e-16 *** regr.nnet -0.879348 0.402810 -2.183 0.029037 * regr.cvglmnet 0.005610 0.004470 1.255 0.209415 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.2349 on 57526 degrees of freedom Multiple R-squared: 0.8173, Adjusted R-squared: 0.8173 F-statistic: 5.148e+04 on 5 and 57526 DF, p-value: < 2.2e-16</code></pre> <p>To back-transform values (y) to ppm use the following formula:</p> <pre><code>ppm = expm1( y / 10 )</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
iSDAsoil: soil extractable Calcium for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil extractable Calcium log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_log.ca_mehlich3_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Calcium mean value,</li> <li>sol_log.ca_mehlich3_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Calcium model (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: log.ca_mehlich3 R-square: 0.84 Fitted values sd: 1.24 RMSE: 0.543 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -6.0376 -0.2577 0.0076 0.2756 5.3825 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 5.737959 3.850998 1.490 0.136 regr.ranger 1.054018 0.003175 331.978 < 2e-16 *** regr.xgboost -0.030930 0.003939 -7.853 4.1e-15 *** regr.cubist 0.061829 0.003561 17.364 < 2e-16 *** regr.nnet -0.855297 0.561006 -1.525 0.127 regr.cvglmnet -0.065040 0.003225 -20.166 < 2e-16 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.5428 on 144593 degrees of freedom Multiple R-squared: 0.8403, Adjusted R-squared: 0.8402 F-statistic: 1.521e+05 on 5 and 144593 DF, p-value: < 2.2e-16 </code></pre> <p>To back-transform values (y) to ppm use the following formula:</p> <pre><code>ppm = expm1( y / 10 )</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
iSDAsoil: soil fine-earth bulk density for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil fine-earth bulk density in 10×kg/m3 predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, <a href="https://landpotential.org/data-portal/">LandPKS</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_db_od_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil bulk density mean value,</li> <li>sol_db_od_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil bulk density model (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: db_od R-square: 0.819 Fitted values sd: 0.269 RMSE: 0.126 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -1.06778 -0.06450 0.00215 0.06585 0.90016 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) -0.05538 0.04860 -1.140 0.25451 regr.ranger 0.86305 0.01577 54.733 < 2e-16 *** regr.xgboost 0.15383 0.01651 9.315 < 2e-16 *** regr.cubist 0.02039 0.01113 1.832 0.06695 . regr.nnet 0.03465 0.03710 0.934 0.35036 regr.cvglmnet -0.03021 0.01032 -2.927 0.00343 ** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.1263 on 13565 degrees of freedom Multiple R-squared: 0.8194, Adjusted R-squared: 0.8193 F-statistic: 1.231e+04 on 5 and 13565 DF, p-value: < 2.2e-16</code></pre> <p>To back-transform values (y) to kg/m-cubic use:</p> <pre><code>kg/m3 = y * 10</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
iSDAsoil: soil extractable Phosphorus for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil extractable Phosphorus (P) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_log.p_mehlich3_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Phosphorus mean value,</li> <li>sol_log.p_mehlich3_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Phosphorus model (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: log.p_mehlich3 R-square: 0.486 Fitted values sd: 0.687 RMSE: 0.707 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -3.2892 -0.3942 -0.0637 0.2614 4.9466 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 3.378801 3.143200 1.075 0.282 regr.ranger 0.861655 0.011099 77.631 < 2e-16 *** regr.xgboost 0.066139 0.013091 5.052 4.38e-07 *** regr.cubist 0.157674 0.008886 17.744 < 2e-16 *** regr.nnet -1.649621 1.442240 -1.144 0.253 regr.cvglmnet 0.013628 0.010407 1.310 0.190 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.7066 on 53493 degrees of freedom Multiple R-squared: 0.486, Adjusted R-squared: 0.486 F-statistic: 1.012e+04 on 5 and 53493 DF, p-value: < 2.2e-16 </code></pre> <p>To back-transform values (y) to ppm use the following formula:</p> <pre><code>ppm = expm1( y / 10 )</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
iSDAsoil: soil extractable Magnesium for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil extractable Magnesium (Mg) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_log.mg_mehlich3_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Magnesium mean value,</li> <li>sol_log.mg_mehlich3_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Magnesium model (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: log.mg_mehlich3 R-square: 0.815 Fitted values sd: 1.05 RMSE: 0.498 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -5.8775 -0.2312 0.0028 0.2465 3.7400 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) -0.034349 0.051219 -0.671 0.5025 regr.ranger 1.034217 0.003263 316.950 <2e-16 *** regr.xgboost -0.008057 0.003854 -2.091 0.0366 * regr.cubist 0.073223 0.003649 20.067 <2e-16 *** regr.nnet -0.017388 0.009528 -1.825 0.0680 . regr.cvglmnet -0.075566 0.003402 -22.213 <2e-16 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.4979 on 136681 degrees of freedom Multiple R-squared: 0.8152, Adjusted R-squared: 0.8152 F-statistic: 1.206e+05 on 5 and 136681 DF, p-value: < 2.2e-16 </code></pre> <p>To back-transform values (y) to ppm use the following formula:</p> <pre><code>ppm = expm1( y / 10 )</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
iSDAsoil: soil stone content for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil stone content / coarse fragments log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_log.wpg2_mehlich3_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil stone content mean value,</li> <li>sol_log.wpg2_mehlich3_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil stone content model (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: log.wpg2 R-square: 0.709 Fitted values sd: 1.25 RMSE: 0.803 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -4.0555 -0.3113 -0.0222 0.2378 4.5794 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) -0.008606 1.361982 -0.006 0.995 regr.ranger 0.972265 0.004443 218.854 < 2e-16 *** regr.xgboost 0.034649 0.006404 5.411 6.3e-08 *** regr.cubist 0.069589 0.005229 13.308 < 2e-16 *** regr.nnet -0.012756 0.796535 -0.016 0.987 regr.cvglmnet -0.056645 0.005509 -10.283 < 2e-16 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.8032 on 92785 degrees of freedom Multiple R-squared: 0.7092, Adjusted R-squared: 0.7092 F-statistic: 4.525e+04 on 5 and 92785 DF, p-value: < 2.2e-16 </code></pre> <p>To back-transform values (y) to % use the following formula:</p> <pre><code>% = expm1( y / 10 )</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
iSDAsoil: soil extractable Sulphur for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil extractable Sulphur (S) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_log.s_mehlich3_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Sulphur mean value,</li> <li>sol_log.s_mehlich3_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Sulphur model (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: log.s_mehlich3 R-square: 0.548 Fitted values sd: 0.423 RMSE: 0.384 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -2.5729 -0.2102 -0.0264 0.1694 5.0049 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 1.459208 4.154229 0.351 0.725 regr.ranger 0.937179 0.016167 57.967 < 2e-16 *** regr.xgboost 0.002587 0.016252 0.159 0.874 regr.cubist 0.145396 0.010890 13.351 < 2e-16 *** regr.nnet -0.672062 1.796642 -0.374 0.708 regr.cvglmnet -0.045157 0.011256 -4.012 6.04e-05 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.3841 on 37530 degrees of freedom Multiple R-squared: 0.5481, Adjusted R-squared: 0.548 F-statistic: 9103 on 5 and 37530 DF, p-value: < 2.2e-16</code></pre> <p>To back-transform values (y) to ppm use the following formula:</p> <pre><code>ppm = expm1( y / 10 )</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
iSDAsoil: soil pH for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
<p>iSDAsoil dataset soil pH (1:1 Soil-Water Suspension) predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as <a href="https://gdal.org/drivers/raster/cog.html">COG</a>. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (<a href="https://www.isda-africa.com/national-soil-services/">iSDA points</a>, <a href="https://www.isric.org/projects/africa-soil-profiles-database-afsp">AfSPDB</a>, and other national and regional soil datasets). Cite as:</p> <p>Hengl, T., Miller, M.A.E., Križan, J. <em>et al.</em> African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. <em>Sci Rep</em> <strong>11, </strong>6130 (2021). <a href="https://doi.org/10.1038/s41598-021-85639-y">https://doi.org/10.1038/s41598-021-85639-y</a></p> <p>To open the maps in QGIS and/or directly compute with them, please use the <a href="https://gitlab.com/openlandmap/africa-soil-and-agronomy-data-cube"><strong>Cloud-Optimized GeoTIFF version</strong></a>.</p> <p>Layer description:</p> <ul> <li>sol_ph_h2o_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil pH mean value,</li> <li>sol_ph_h2o_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil pH model (prediction) errors,</li> </ul> <p>Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (<a href="https://mlr.mlr-org.com/reference/makeStackedLearner.html">mlr::makeStackedLearner</a>) for this variable indicates:</p> <pre><code>Variable: ph_h2o R-square: 0.818 Fitted values sd: 0.972 RMSE: 0.459 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -5.5939 -0.2328 -0.0066 0.2222 4.7477 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 1.113440 1.164473 0.956 0.338986 regr.ranger 1.032918 0.003138 329.116 < 2e-16 *** regr.xgboost -0.014201 0.004185 -3.393 0.000691 *** regr.cubist 0.049667 0.003709 13.392 < 2e-16 *** regr.nnet -0.188570 0.188214 -1.002 0.316398 regr.cvglmnet -0.059763 0.003636 -16.438 < 2e-16 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.4591 on 133378 degrees of freedom Multiple R-squared: 0.8176, Adjusted R-squared: 0.8176 F-statistic: 1.195e+05 on 5 and 133378 DF, p-value: < 2.2e-16</code></pre> <p>To back-transform values (y) to index use:</p> <pre><code>index = y / 10</code></pre> <p>To submit an issue or request support please visit <a href="https://isda-africa.com/isdasoil"><strong>https://isda-africa.com/isdasoil</strong></a></p>
Defect Prediction Tool Validation Dataset 2
<p><strong>This dataset is used to address the Research Questions in the study at Transactions on Software Engineering</strong>: <strong>Within-Project</strong> <strong>Defect Prediction of Infrastructure-as-Code using Product and Process Metrics. </strong></p> <p><strong>See also: https://github.com/stefanodallapalma/TSE-2020-05-0217.</strong></p> <p>It provides</p> <p>* <strong>repositories.json</strong> - a list of repositories selected from open-source GitHub repositories based on the Ansible language.</p> <p>* <strong>fixing-commits.json</strong> - a list of defect-fixing commits extracted from those repositories.</p> <p>* <strong>fixed-files.json</strong> - a list of Ansible files fixed in those defect-fixing commits and respective bug-inducing commits.</p> <p>* <strong>failure-prone-files.json</strong> - a list of failure-prone files through the repository's commit history.</p> <p>* <strong>metrics.zip </strong>- csv files consisting of releases (set of files) and their IaC-oriented, delta and process metrics extracted from each analyzed repository</p> <p>* <strong>projects.zip </strong>- for each analyzed project, it contains the data (models, performance, and results of Recursive Feature Elimination) used to answer the Research Questions.</p> <p><strong>Context</strong></p> <p><em>Infrastructure-as-code (IaC)</em> is the DevOps strategy that allows management and provisioning of infrastructure through the definition of machine-readable files and automation around them, rather than physical hardware configuration or interactive configuration tools.</p> <p>On the one hand, although IaC represents an ever-increasing widely adopted practice nowadays, still little is known concerning how to best maintain, speedily evolve, and continuously improve the code behind the IaC strategy in a measurable fashion. <br> On the other hand, source code measurements are often computed and analyzed to evaluate the different quality aspects of the software developed.<br> In particular, Infrastructure-as-Code is simply "code", as such it is prone to defects as any other programming languages.</p> <p>This dataset targets the YAML-based Ansible language to devise <strong>within-project defects prediction</strong> approaches for IaC based on Machine-learning.</p> <p><strong>Content</strong></p> <p>The dataset contains metrics extracted from 85 open-source GitHub repositories based on the Ansible language that satisfied the following criteria:</p> <p>* The repository has at least one push event to its master branch in the last six months;<br> * The repository has at least 2 releases;<br> * At least 10% of the files in the repository are IaC scripts;<br> * The repository has at least 2 core contributors;<br> * The repository has evidence of continuous integration practice, such as the presence of a .travis.yaml file;<br> * The repository has a comments ratio of at least 0.1%;<br> * The repository has commit frequency of at least 2 per month on average;<br> * The repository has an issue frequency of at least 0.01 events per month on average;<br> * The repository has evidence of a license, such as the presence of a LICENSE.md file<br> * The repository has at least 100 source lines of code.</p> <p>Metrics are grouped into three categories:</p> <p>* <strong>IaC-Oriented:</strong> metrics of structural properties derived from the source code of infrastructure scripts. Click [here](https://www.sciencedirect.com/science/article/pii/S0164121220301618) for more info.</p> <p>* <strong>Delta</strong>: metrics that capture the amount of change in a file between two successive releases, collected for each IaC-oriented metric.</p> <p>* <strong>Process</strong>: metrics that capture aspects of the development process rather than aspects about the code itself. Description of the process metrics in this dataset can be found [here](https://pydriller.readthedocs.io/en/latest/processmetrics.html).</p> <p>In addition to the metrics, the dataset contains the pre-trained models (*.joblib) in the folders rq1 and rq2 of projects.zip.</p> <p>You can load the model in Python as follows:</p> <p>```<br> from joblib import load<br> model = load('projects/owner/repository/rq1/random_forest.joblib'), mmap_mode='r')</p> <p>best_estimator = model['estimator'] # The estimator that maximized the AUC-PR</p> <p>cv_results = model['cv_results'] # The results of each step of the validation procedure</p> <p>best_index = mode['best_index'] # The index to access the best cv_results<br> ```</p> <p> </p> <p><strong>Acknowledgements</strong></p> <p> </p> <p>This work is supported by the European Commission grants no. 825040 (RADON H2020).</p> <p><br> <strong>Inspiration</strong></p> <p>What source code properties and properties about the development process are good predictors of defects in Infrastructure-as-Code scripts?</p>
An integrated polygenic tool substantially enhances coronary artery disease prediction
<p>Summary-level CAD GWAS data generated by Genomics plc as presented in:</p> <p>Riveros-Mckay F. et al. An integrated polygenic tool substantially enhances coronary artery disease prediction. Circulation: Genomics and Precision Medicine (in press). </p> <p>If you have any questions or comments regarding these files, please contact Genomics plc at research@genomicsplc.com</p> <p> </p> <p>NOTES<br> -----------------------------<br> These analyses were carried out using the full UK Biobank imputation data release (v3b). Analyses were restricted to a subset of UK Biobank, described as “Group I” in the published paper. Group I, “no PCE/QRISK3 available”, included 114,196 European-ancestry individuals with missing data that prevented PCE or QRISK3 calculation.</p> <p>CAD case phenotypes were defined as described in the “Phenotype definitions” section of the paper’s Supplementary Materials, using both prevalent (pre-baseline) and incident (post-baseline) events.</p> <p>All analyses included Age at assessment, sex, genotyping chip, and 10 principal components as covariates. </p> <p>We used plink2.0 logistic regression. For chromosome X variants males were treated as having 0 or 2 alternative alleles. </p> <p>The results are not adjusted for genomic control.</p> <p> </p> <p>DATA FILE CONTENT DESCRIPTION<br> -----------------------------<br> cpra Variant ID in ‘CPRA’ format. Position reflects position in b37. <br> chrom Chromosome<br> pos Position in base pairs (b37, 1-based)<br> alt Alternative allele (effect allele)<br> beta Effect size (log odds ratio)<br> standard_error Standard error of beta <br> minus_log10_p Minus log(base 10) of P-value<br> ref Reference allele (non-effect allele)<br> ncase Number of cases<br> ncontrol Number of controls</p>
Ecology and environment predict spatially stratified risk of H5 highly pathogenic avian influenza clade 2.3.4.4b in wild birds across Europe
<p>The data in this repository were used to conduct the analysis outlined in the following bioRxiv preprint:</p> <ul> <li>Sarah Hayes, Joe Hilton, Joaquin Mould-Quevedo, Christl Donnelly, Matthew Baylis, Liam Brierley (2025) "Ecology and environment predict spatially stratified risk of H5 highly pathogenic avian influenza clade 2.3.4.4b in wild birds across Europe" <em>bioRxiv</em> doi:10.1101/2024.07.17.603912</li> </ul> <p>The codes used for the analyses are available at https://github.com/sarahhayes/avian_flu_sdm/ </p> <p>The following lookup table can be used to cross-reference between the variable descriptions in Tables 1 and 2 of the preprint and the files in this repository:</p> <p> </p> <table> <tbody> <tr> <td> <h3> Variable description </h3> </td> <td> <h3> Filename </h3> </td> </tr> <tr> <td> Minimum elevation (metres above sea level) </td> <td> elevation_min_10kres.tif </td> </tr> <tr> <td> Maximum elevation (metres above sea level) </td> <td> elevation_max_10kres.tif </td> </tr> <tr> <td> Difference between minimum and maximum elevation </td> <td> elevation_diff_10kres.tif </td> </tr> <tr> <td> Modal elevation (metres above sea level) </td> <td> elevation_mode_10kres.tif </td> </tr> <tr> <td> Normalised Difference Vegetation Index (NDVI) </td> <td> ndvi_*_quart_2022_eco_rasts.tif </td> </tr> <tr> <td> Land cover </td> <td> landcover_output_full_2022_10kres.tif </td> </tr> <tr> <td> Distance to coast </td> <td> dist_to_coast_10kres.csv </td> </tr> <tr> <td> Distance to inland water </td> <td> dist_to_water_output_10kres.csv </td> </tr> <tr> <td> Relative humidity </td> <td> mean_relative_humidity_q*_10kres_eco_quarts.tif </td> </tr> <tr> <td>Seasonal weighted mean of the month-wise difference in the minimum temperature and maximum temperature (degrees Celsius) </td> <td> mean_diff_*_quart_eco_rasts.tif </td> </tr> <tr> <td>Seasonal weighted mean of monthly mean temperatures (degrees Celsius) (Mean monthly temperature for each month calculated using: Mean temperature = Minimum temperature + diurnal range/2)</td> <td> mean_mean_*_quart_eco_rasts.tif </td> </tr> <tr> <td>Seasonal temperature variation (degrees Celsius)<br>(Difference between the maximum and minimum of<br>mean monthly temperature values across months<br>majority-represented within the season)</td> <td> variation_in_quarterly_mean_temp_q*_eco_rasts.tif </td> </tr> <tr> <td> Precipitation </td> <td> mean_prec_*_quart_eco_rasts.tif </td> </tr> <tr> <td>Seasonal mean of daily zero-degree isotherm (metres<br>above sea level) </td> <td> isotherm_mean_q*_eco_rasts.tif </td> </tr> <tr> <td>Number of days the zerodegree isotherm was below 1 metre at midday at Coordinated Universal Time (UTC) </td> <td> isotherm_midday_days_below1_q*_eco_quarts.tif </td> </tr> <tr> <td> Chicken density </td> <td> chicken_density_2010_10kres.tif </td> </tr> <tr> <td> Duck density </td> <td> duck_density_2010_10kres.tif </td> </tr> <tr> <td> <em>Anatinae</em> (dabbling ducks) </td> <td> anatinae_rast_eco_bds.tif </td> </tr> <tr> <td> <em>Anserinae</em> (swans and geese) </td> <td> anserinae_rast_eco_bds.tif </td> </tr> <tr> <td> <em>Ardeidae</em> (herons) </td> <td> ardeidae_rast_eco_bds.tif </td> </tr> <tr> <td> <em>Arenaria/Calidris</em> (turnstones and sandpipers) </td> <td> arenaria_calidris_rast_eco_bds.tif </td> </tr> <tr> <td> <em>Aythyini</em> (diving ducks)</td> <td> aythyini_rast_eco_bds.tif</td> </tr> <tr> <td> Laridae (gulls) </td> <td> laridae_rast_eco_bds.tif </td> </tr> <tr> <td> Percentage time spent feeding within 2m of water surface </td> <td> around_surf_rast_eco_bds.tif </td> </tr> <tr> <td> Percentage time spent feeding >2m below water surface </td> <td> below_surf_rast_eco_bds.tif </td> </tr> <tr> <td> Percentage diet plants </td> <td> plant_rast_eco_bds.tif </td> </tr> <tr> <td> Percentage diet scavenging </td> <td> scav_rast_eco_bds.tif </td> </tr> <tr> <td> Percentage diet endothermic vertebrates </td> <td> vend_rast_eco_bds.tif </td> </tr> <tr> <td> Congregative </td> <td> cong_rast_eco_bds.tif </td> </tr> <tr> <td> Migratory </td> <td> migr_rast_eco_bds.tif </td> </tr> <tr> <td> Below threshold phylogenetic distance to known host species </td> <td> host_dist_rast_eco_bds.tif </td> </tr> <tr> <td> Species richness </td> <td> species_richness_rast_eco_bds.tif </td> </tr> </tbody> </table>
TAILVAR (Terminal codon Analysis and Improved prediction of Lengthened VARiants)
<p>This dataset includes relevant files for developing the TAILVAR score designed to assess the functional impact of <strong>stop-loss variants</strong> occurring at stop codons (TAA, TGA, TAG). <strong>TAILVAR</strong> is built using a Random Forest model that predicts the pathogenicity of <strong>stop-loss variants</strong>. By integrating a combination of in-silico prediction scores, transcript features, and protein context information, <strong>TAILVAR</strong> provides a score ranging from 0 to 1, indicating the probability of a variant being pathogenic.</p> <p>For more information, please visit <a href="https://github.com/dr-yoon/TAILVAR">https://github.com/dr-yoon/TAILVAR</a></p>
Results: Predicted cooling effect, deaths prevented and associated economic value from public green spaces in Paris V2
<p>This dataset represents results predicting the cooling effect, deaths prevented and associated economic value for public green spaces in Paris for 40 hot days above the minimum mortality threshold in 2019. </p> <p>This is version 2. The value of a statistical life (VSL) has been corrcted and all values adjusted. </p> <p>The data format is a shapefile with coordinate reference system RGF93 v1 / Lambert-93 (EPSG:2154).</p> <p>Please see the Variable_name csv file for description of the variable names. </p> <p>The (non-reproducible) code is available at https://github.com/j-k-garrett/REGREEN_Paris_heat</p> <p>These results are from the submitted (September 2025) paper entitled:</p> <p><strong><span>Nature-Based Solutions for Urban Heat: Health and Economic Value of Paris’s Public Green Spaces</span></strong></p> <p>Authored by:</p> <p>Joanne K. Garrett<sup>1</sup>, David Neil Bird<sup>2</sup>, Timothy J. Taylor<sup>1</sup>, Elizabeth McCarthy<sup>3</sup>, David H. Fletcher<sup>4</sup>, Benedict W. Wheeler<sup>1</sup>, Marianne Zandersen<sup>5</sup>, Laurence Jones<sup>3</sup></p> <p><sup>1</sup>European Centre for Environment and Human Health, University of Exeter, Penryn, Cornwall, UK</p> <p><sup>2 </sup>Institute for Climate, Energy and Society, JOANNEUM RESEARCH, Graz, Austria</p> <p><sup>3</sup> Department of Environmental Studies, Schiller Institute for Integrated Science and Society, Boston College, USA</p> <p><sup>4</sup> UK Centre for Ecology & Hydrology, Environment Centre Wales, Bangor, Gwynedd, Wales, UK</p> <p><sup>5 </sup>Department of Environmental Science, iClimate Interdisciplinary Centre for Climate Change, Aarhus University, Denmark</p> <p> </p>
Dataset to: Organic carbon stocks, quality and prediction in permafrost-affected forest soils in North Canada (CATENA) - Version 2 (Corrected)
<p><strong>Version update: Coordinates were not correct in previsous version and have been corrected now in version 2</strong></p> <p> </p> <p>Dataset to the manuscript: Schiedung et al. (2022, Catena) Organic carbon stocks, quality and prediction in permafrost-affected forest soils in North Canada ( <a href="https://doi.org/10.1016/j.catena.2022.106194">https://doi.org/10.1016/j.catena.2022.106194</a> )</p> <p>Data files, variables and parameter are described in <em>Var_names_dd_all.csv</em> for all data on each sample and <em>Var_names_dd_composites.csv </em>for all data on composited samples per site and depth. DRIFT data and corresponding explenation are in <em>Schiedung_CATENA_DRIFT_v1.1.zip.</em></p> <p> </p> <p><strong> </strong></p>
GEOLAB Blind Prediction Contest - Supporting Documentation
<p>As part of the <a href="https://project-geolab.eu/">GEOLAB project</a>, the Institute of Geotechnics of TU Darmstadt called geotechnical engineers from industry and academia to participate in an international Blind Prediction Contest (BPC) on the response of piles under monotonic and cyclic lateral loading. Two separate tests were performed on a hollow open-ended steel pile embedded in dry sand. One test under monotonic loading and the other under quasi-static harmonic loading with more than 10,000 loading cycles.</p> <p>Contestant teams were allowed to submit predictions for both tests or for the monotonic test only. The predictions were objectively marked based on their discrepancy with the experimental values. The teams with the higher score in the prediction of each test were publicly announced. The rest of the submitted predictions will be anonymised and used for assessing the state of the art and the state of practice by the organiser committee.</p> <p>This dataset includes the supporting documentation provided to the participants. </p>
Datasets from study: "Land surface observations boost temperature forecast skill: experiments using Long Short-Term Memory surrogate for physics-based models to assess potential predictability"
<p>This repository contains the datasets needed to reproduce the figures from manuscript: Land surface observations boost temperature forecast skill: experiments using Long Short-Term Memory surrogate for physics-based models to assess potential predictability.</p> <p>In this study, we examine the potential of land surface temperature and vegetation data, which are not routinely assimilated in NWP models, for enhancing temperature forecast skill. We build surrogate models for NWP using Long Short-Term Memory.</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.