mariana gomez - Academia.edu (original) (raw)

Papers by mariana gomez

<p>Groundwater level forecasting with machine learning has been widely studied due ... more <p>Groundwater level forecasting with machine learning has been widely studied due to its generally accurate results and little input data requirements. Furthermore, machine learning models for this purpose are set up and trained in a short time when compared to the effort required for process-based, numerical models. Despite the high performance of models obtained at specific locations, applying the same model architecture to multiple sites across a regional area might lead to contrasting accuracies. Likely causalities of this discrepancy in model performance have been barely examined in previous studies. Here, we investigate the link between model performance and the effects of geospatial site characteristics and time series features. Using precipitation and temperature as predictors, we model groundwater levels at approximately 500 observation wells in Lower Saxony, Germany, using a 1-D convolutional neural network with a fixed architecture and hyperparameters tuned for each time series individually. The performances are evaluated against geospatial and time series features using correlation coefficients. Model performance is negatively influenced at sites near waterworks and densely vegetated areas. Besides, the more complex the time series, the higher the metrics, but autocorrelation reduces the model performance. The new insights evidence that further information is required at certain locations to improve model accuracy due to external impacts.  </p>

<p>In the field of spatial machine learning, access to high-quality data sets is a ... more <p>In the field of spatial machine learning, access to high-quality data sets is a crucial factor in the success of any analysis or modeling project, especially in subsurface hydrology. However, finding and utilizing such data sets can be a challenging and time-consuming process. This is where AwesomeGeodataTable comes in. AwesomeGeodataTable aims to establish a community-maintained searchable table of data sets that are easily usable as predictors for spatial machine learning starting with the focus on subsurface hydrology. With its user-friendly interface and currently small but growing number of data sets, AwesomeGeodataTable will make it easier for researchers and practitioners to find and use the data they need for their work. It brings the usability of existing data set collections to a next level through adding features for filtering and searching meta information on data sets. This talk will introduce attendees to the AwesomeGeodataTable project, its goals and features, and how they can get involved in maintaining and extending its database and expanding its features and user experience. Overall, AwesomeGeodataTable is a valuable resource for anyone working in the field of spatial machine learning, and we hope to see it become a widely used and respected resource in the community.</p>

2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2007

... [11] DO Morgan, "Regulation of the APC and the exit from mitosis," Nat Cell Biol, v... more ... [11] DO Morgan, "Regulation of the APC and the exit from mitosis," Nat Cell Biol, vol. 1, pp. E47-53, 1999. [12] SK Chanda, S. White, AP Orth, R. Reisdorph, L. Miraglia, RS Thomas, P.DeJesus, DE Mason, Q. Huang, R. Vega, DH Yu, CG Nelson, BM Smith, R. Terry, AS Linford, ...

European Journal of Neuroscience, 1994

Three cDNAs (ALS, Da2 and ARD) isolated from the nervous system of Drosophila and encoding putati... more Three cDNAs (ALS, Da2 and ARD) isolated from the nervous system of Drosophila and encoding putative nicotinic acetylcholine receptor subunits were expressed in Xenopus oocytes in order to study their functional properties. Functional receptors could not be reconstituted from any of these subunits taken singly or in twos and threes. In contrast, large evoked currents (in the pA range) were consistently observed upon agonist application on oocytes co-injected with ALS or Da2 in combination with the chick p2 structural subunit. The ALSO2 and Da2/p2 receptors are highly sensitive to acetylcholine and nicotine, and their physiological properties resemble those of native or reconstituted receptors from vertebrates. Although the physiological properties of ALSIp2 and Da2/p2 receptors are quite similar, clear differences appear in their pharmacological profiles. The ALSIp2 receptor is highly sensitive to a-bungarotoxin while the Da21p2 receptor is totally insensitive to this agent. These results demonstrate that the Drosophila ALS and Da2 cDNAs encode neuronal nicotinic subunits responding to physiological concentrations of the agonists acetylcholine and nicotine.

<p>Groundwater level forecasting with machine learning has been widely studied due ... more <p>Groundwater level forecasting with machine learning has been widely studied due to its generally accurate results and little input data requirements. Furthermore, machine learning models for this purpose are set up and trained in a short time when compared to the effort required for process-based, numerical models. Despite the high performance of models obtained at specific locations, applying the same model architecture to multiple sites across a regional area might lead to contrasting accuracies. Likely causalities of this discrepancy in model performance have been barely examined in previous studies. Here, we investigate the link between model performance and the effects of geospatial site characteristics and time series features. Using precipitation and temperature as predictors, we model groundwater levels at approximately 500 observation wells in Lower Saxony, Germany, using a 1-D convolutional neural network with a fixed architecture and hyperparameters tuned for each time series individually. The performances are evaluated against geospatial and time series features using correlation coefficients. Model performance is negatively influenced at sites near waterworks and densely vegetated areas. Besides, the more complex the time series, the higher the metrics, but autocorrelation reduces the model performance. The new insights evidence that further information is required at certain locations to improve model accuracy due to external impacts.  </p>

<p>In the field of spatial machine learning, access to high-quality data sets is a ... more <p>In the field of spatial machine learning, access to high-quality data sets is a crucial factor in the success of any analysis or modeling project, especially in subsurface hydrology. However, finding and utilizing such data sets can be a challenging and time-consuming process. This is where AwesomeGeodataTable comes in. AwesomeGeodataTable aims to establish a community-maintained searchable table of data sets that are easily usable as predictors for spatial machine learning starting with the focus on subsurface hydrology. With its user-friendly interface and currently small but growing number of data sets, AwesomeGeodataTable will make it easier for researchers and practitioners to find and use the data they need for their work. It brings the usability of existing data set collections to a next level through adding features for filtering and searching meta information on data sets. This talk will introduce attendees to the AwesomeGeodataTable project, its goals and features, and how they can get involved in maintaining and extending its database and expanding its features and user experience. Overall, AwesomeGeodataTable is a valuable resource for anyone working in the field of spatial machine learning, and we hope to see it become a widely used and respected resource in the community.</p>

2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2007

... [11] DO Morgan, "Regulation of the APC and the exit from mitosis," Nat Cell Biol, v... more ... [11] DO Morgan, "Regulation of the APC and the exit from mitosis," Nat Cell Biol, vol. 1, pp. E47-53, 1999. [12] SK Chanda, S. White, AP Orth, R. Reisdorph, L. Miraglia, RS Thomas, P.DeJesus, DE Mason, Q. Huang, R. Vega, DH Yu, CG Nelson, BM Smith, R. Terry, AS Linford, ...

European Journal of Neuroscience, 1994

Three cDNAs (ALS, Da2 and ARD) isolated from the nervous system of Drosophila and encoding putati... more Three cDNAs (ALS, Da2 and ARD) isolated from the nervous system of Drosophila and encoding putative nicotinic acetylcholine receptor subunits were expressed in Xenopus oocytes in order to study their functional properties. Functional receptors could not be reconstituted from any of these subunits taken singly or in twos and threes. In contrast, large evoked currents (in the pA range) were consistently observed upon agonist application on oocytes co-injected with ALS or Da2 in combination with the chick p2 structural subunit. The ALSO2 and Da2/p2 receptors are highly sensitive to acetylcholine and nicotine, and their physiological properties resemble those of native or reconstituted receptors from vertebrates. Although the physiological properties of ALSIp2 and Da2/p2 receptors are quite similar, clear differences appear in their pharmacological profiles. The ALSIp2 receptor is highly sensitive to a-bungarotoxin while the Da21p2 receptor is totally insensitive to this agent. These results demonstrate that the Drosophila ALS and Da2 cDNAs encode neuronal nicotinic subunits responding to physiological concentrations of the agonists acetylcholine and nicotine.