| 2. |
- Al Banna, Md. Hasan, et al.
(författare)
-
Attention-based Bi-directional Long-Short Term Memory Network for Earthquake Prediction
- 2021
-
Ingår i: IEEE Access. - : IEEE. - 2169-3536. ; 9, s. 56589-56603
-
Tidskriftsartikel (refereegranskat)abstract
- An earthquake is a tremor felt on the surface of the earth created by the movement of the major pieces of its outer shell. Till now, many attempts have been made to forecast earthquakes, which saw some success, but these attempted models are specific to a region. In this paper, an earthquake occurrence and location prediction model is proposed. After reviewing the literature, long short-term memory (LSTM) is found to be a good option for building the model because of its memory-keeping ability. Using the Keras tuner, the best model was selected from candidate models, which are composed of combinations of various LSTM architectures and dense layers. This selected model used seismic indicators from the earthquake catalog of Bangladesh as features to predict earthquakes of the following month. Attention mechanism was added to the LSTM architecture to improve the model’s earthquake occurrence prediction accuracy, which was 74.67%. Additionally, a regression model was built using LSTM and dense layers to predict the earthquake epicenter as a distance from a predefined location, which provided a root mean square error of 1.25.
|
|
| 3. |
- Rincon, Jonathan, 1991-, et al.
(författare)
-
Textural and chemical characterization of sulphide minerals for improved beneficiation and exploration at the Rävliden Norra VMS deposit, Skelleftedistrict, Sweden
- 2020
-
Ingår i: Abstracts and Proceedings of the Geological Society of Norway. - Oslo : Norsk Geologisk Forening. ; , s. 179-180
-
Konferensbidrag (refereegranskat)abstract
- The Rävliden Norra VMS deposit, represents one of the most important new discoveries in the Skellefte district (SD) in this decade. The mineralization is hosted at the transition between Skellefte group rocks (SG), dominated by coherent rhyolitic and dacitic meta-volcanic rocks, and the Vargfors group (VG), composed of metasedimentary graphitic shale interbedded with crystal-rich, monomictic to polymictic, clast-supported mass flow deposits. The ore lenses contain massive sphalerite + galena + pyrite + pyrrhotite + chalcopyrite ± Ag-Sb-Pbsulphosalts, structurally and stratigraphically above chalcopyrite + pyrrhotite stringer mineralization. The hanging wall rocks (VG) host pyrite + pyrrhotite ± arsenopyrite mineralization. Alteration in the footwall rocks, consists of sericite, chlorite, quartz, pyrite, tremolite, actinolite, carbonate and talc. The hanging wall is less altered with limited sericite or chlorite associated with minor carbonate alteration. Post ore modifications occur as, e.g. sulphides in pressure shadows, infilling of syntectonic tension gashes, “durchbewegung” texture, and sulphide-rich veins that crosscut hanging wall rocks. Significant changes in the distribution and deportment of trace and precious elements within the deposit are evident, however the implications of these on mineral processing performance and exploration vectoring has not previously been assessed in other VMS deposits in the SD. To this end, the presence of pyrite and remobilised sulphides in both hanging wall and footwall of the Rävliden Norra mineralizations, provides an opportunity to evaluate enrichment or depletion of elements hosted in the sulphide lattices or as inclusions using LA-ICP-MS. In-situ SIMS analyses in sulphide phases will allow discrimination between sedimentary and hydrothermal sulphur in the system. An investigation into the deportment of In, Ga and Ge in sphalerite and galena, will be the first assessment of these critical elements in a VMS deposit in the SD. Ultimately, integration of elemental distribution and mineral features, such as modal mineralogy, liberation degree, and grain size, with processing variables, e.g. mineral recovery, grade or flotation kinetics; will provide a better understanding of the ore performance during concentration and beneficiation.
|
|
