The Use of Machine Learning for Accessing Landslide Susceptibility Class: Study Case of Kecamatan Pacet, Kabupaten Mojokerto

Kecamatan Pacet, Kabupaten Mojokerto is one of an area with many landslide events in East Java Province. As a mitigation effort, this research aimed to map the landslide susceptibility class distribution of the research area. This research applied a machine learning analysis technic which combined Frequency Ratio (FR) and Logistic Regression (LR) models to assess the landslide susceptibility class distribution. FR bivariate analysis is used to normalized the data and to identify the influence significancy on each class of triggering factors. LR multivariate analysis is applied to generate the landslide probability (susceptibility) and to show the influence significancy of each triggering factor to landslide events. There are 12 triggering factors to landslide used in this research, which is: TPI, TWI, SPI, slope, aspect, elevation, profile curvature, distance to drainage, geological unit, rainfall, land use, and distance to the road. This research has 383 landslides and 383 non-landslide events as the data sample based on field survey, BPBD Kabupaten Mojokerto, and Google Earth Pro imagery interpretation. The proportion of dataset training and testing is 70% and 30%, which generated from the data inventory. This research used ROC analysis to validate the landslide susceptibility model. The result showed that the landslide susceptibility model has an AUC value of 0.91, which indicated that the model has high accuracy.

Multi-predictor mapping of soil organic carbon in the alpine tundra: a case study for the central Ecuadorian páramo

Background Soil organic carbon (SOC) affects essential biological, biochemical, and physical soil functions such as nutrient cycling, water retention, water distribution, and soil structure stability. The Andean páramo known as such a high carbon and water storage capacity ecosystem is a complex, heterogeneous and remote ecosystem complicating field studies to collect SOC data. Here, we propose a multi-predictor remote quantification of SOC using Random Forest Regression to map SOC stock in the herbaceous páramo of the Chimborazo province, Ecuador. Results Spectral indices derived from the Landsat-8 (L8) sensors, OLI and TIRS, topographic, geological, soil taxonomy and climate variables were used in combination with 500 in situ SOC sampling data for training and calibrating a suitable predictive SOC model. The final predictive model selected uses nine predictors with a RMSE of 1.72% and a R2 of 0.82 for SOC expressed in weight %, a RMSE of 25.8 Mg/ha and a R2 of 0.77 for the model in units of Mg/ha. Satellite-derived indices such as VARIG, SLP, NDVI, NDWI, SAVI, EVI2, WDRVI, NDSI, NDMI, NBR and NBR2 were not found to be strong SOC predictors. Relevant predictors instead were in order of importance: geological unit, soil taxonomy, precipitation, elevation, orientation, slope length and steepness (LS Factor), Bare Soil Index (BI), average annual temperature and TOA Brightness Temperature. Conclusions Variables such as the BI index derived from satellite images and the LS factor from the DEM increase the SOC mapping accuracy. The mapping results show that over 57% of the study area contains high concentrations of SOC, between 150 and 205 Mg/ha, positioning the herbaceous páramo as an ecosystem of global importance. The results obtained with this study can be used to extent the SOC mapping in the whole herbaceous ecosystem of Ecuador offering an efficient and accurate methodology without the need for intensive in situ sampling.

Modified Archie’s parameters for estimating water saturation for carbonate reservoir in north of Iraq

Archie’s parameters, cementation factor (m), saturation exponent (n) and tortuosity factor (a), are general factor that have effects on water saturation magnitude, due to their sensitivity to pores distribution, lithofacies properties and wettability, particularly in carbonate reservoirs. Water saturation magnitude has a direct effect in estimating initial oil-in-place values, and inaccuracy in its values will lead to huge impact errors in initial oil-in-place values, so it would affect the economics of field management and development plans. In this paper, the main objective was to investigate the impact of using conventional and modified Archie’s parameters in the determination of water saturation from well log interpretation for Tertiary reservoir in Khabaz oil field, a heterogenous carbonite reservoir in the north of Iraq which was affected by different digenesis processes that impacted the reservoir quality. Tertiary reservoir of Khabaz field consists of five geological units (A, B, C, D and E), and the selected well penetrated the top of the reservoir at 2200.5 m RTKB and passed through five geological units and reached total depth at 2348 m RTKB. The geothermal gradient of the field was 1.12 ℉ per 100 ft, and formation water resistivity (Rw) was about 0.029 Ω m. Water saturation was at first estimated from resistivity logs by Archie model with conventional known values of parameters (a, m and n) (1, 2 and 2), respectively, and then Archie’s parameters were modified and determined by graphical technique of Pickett plot for each geological unit to estimate water saturation. Finally, the results show the water saturation value was more sensitive for Archie’s parameter in low-porosity and high-clay-volume zone, but less sensitive in clean high-porosity zone, and water saturation values determined by modified Archie model were less about 18.5% at mean than their value by using conventional Archie’s parameters.

Geochemical Characteristics and Ecological Risk Assessment of Heavy Metals in Surface Soil of Gaomi City

Gaomi City, the hinterland of Jiaolai Plain in Shandong Peninsula, was selected as the research object. A total of 8197 surface soil samples were collected to determine the contents of eight soil heavy metals (HMs)including Copper (Cu), Lead (Pb), Zinc (Zn), Nickel (Ni), Chromium (Cr), Cadmium (Cd), Arsenic (As), and Mercury (Hg). Statistical methods were used to find out the geochemical background (GCB) in the area, systematic clustering and factor analysis were used to study the homology between HMs, and single-factor evaluation method was used to evaluate the ecological risks in the study area. The results of the study show that the ecological risk of the surface soil in the study area is relatively low, dominated by a planar distribution, with only a few high-risk points. The uneven distribution of Hg in the surface soil is affected by human activities to a certain extent. The ratio of the GCB of the geological unit area to the GCB of the whole area shows that the Hg content of the Qingshan Group and Dasheng Group geological units is higher, and the Pb content in the subvolcanic rock area is slightly higher. The ecological pollution risk in the study area is generally low, and only exists individual high-risk areas, distributed radially in densely populated areas.

Three-Dimensional Structural Geological Modeling Using Graph Neural Networks

Three-dimensional structural geomodels are increasingly being used for a wide variety of scientific and societal purposes. Most advanced methods for generating these models are implicit approaches, but they suffer limitations in the types of interpolation constraints permitted, which can lead to poor modeling in structurally complex settings. A geometric deep learning approach, using graph neural networks, is presented in this paper as an alternative to classical implicit interpolation that is driven by a learning through training paradigm. The graph neural network approach consists of a developed architecture utilizing unstructured meshes as graphs on which coupled implicit and discrete geological unit modeling is performed, with the latter treated as a classification problem. The architecture generates three-dimensional structural models constrained by scattered point data, sampling geological units and interfaces as well as planar and linear orientations. The modeling capacity of the architecture for representing geological structures is demonstrated from its application on two diverse case studies. The benefits of the approach are (1) its ability to provide an expressive framework for incorporating interpolation constraints using loss functions and (2) its capacity to deal with both continuous and discrete properties simultaneously. Furthermore, a framework is established for future research for which additional geological constraints can be integrated into the modeling process.

PETROGRAPHIC CHARACTERIZATION AND DIAGENESIS IN SANDSTONES OUTCROPS OF THE NORTHERN MACEIÓ FORMATION: IMPLICATIONS IN RESERVOIR QUALITY

The acquisition of geological data is of fundamental importance for the study of areas potentially relevant to the occurrence of petroleum systems. In this context, the development of research in outcropping rock formations has proven to be a potential method to investigate the geology of the geological unit studied in subsurface. One of several examples found in Brazil are the outcrops Barreiras do Boqueirão and Praia de Japaratinga, belonging to the Maceió Formation, located in the northern coast of Alagoas State. The Maceió Formation has the lowest cretaceous sedimentation record within the Alagoas Basin. This sedimentation, present almost in the entire basin, is located mainly in its subsurface. This geological unit is composed of several lithologies, including a turbiditic sequence predominantly formed by shales, sandstones and conglomerates. This environment makes it possible the occurrence of a petroleum system. Our research group chose to investigate this environment because turbiditic sandstones are excellent petroleum reservoirs, and they have a great economic relevance in the Brazilian petroleum scenario. To develop this research, a petrographic characterization of the Maceió Formation sandstones was conducted to help determine the compositional and diagenetic aspects of these rocks and infer the influence of diagenetic processes on the quality of these sandstones as reservoirs. The petrographic analysis showed that the studied sandstones can be classified as arkose and quartzenite, present moderate porosity and good permeability, observed through the predominant presence of floating contacts between the grains. The porosity is predominantly primary intergranular, averaging 15%, but secondary porosity by fracture and dissolution of primary grains also occurs. The sandstones of the Maceió Formation are poorly and moderately selected, with angular, sub-angular and sub-rounded grains, showing low to medium textural maturity, which may also influence the quality of the reservoir, impairing the primary porosity in the samples. The three diagenetic stages were identified as: eodiagenesis, mesodiagenesis, and telodiagenesis. The diagenetic processes found were: mechanical compaction, beginning of chemical compaction, clay infiltration, pyrite cementation, grain dissolution, chlorite cementation, quartz sintaxial growth, and mineral alteration and replacement. Mineral replacement was a phenomenon observed quite expressively in the samples analyzed. This event was evidenced, particularly, by the substitution of muscovite and feldspar for kaolinite, the alteration of biotite was also identified in the samples. Therefore, one can infer that the diagenetic processes had little influence on the reduction of the original porosity in the samples studied. In general, considering all the analyses performed in this research, one can see that the sandstones of the Maceió Formation (northern portion) present a good reservoir quality.

Predicting Fault Locations based on Morphometric Features of Alluvial Fans and Basins using Artificial Neural Networks

The aim of this study is to investigate the morphometry of alluvial fans located in the vicinity of the Sabzevar and Sang-Sefid faults in northeastern Iran to determine their influence on erosion Principal component analysis (PCA) was used to select the most important morphometric factors affecting erosion. The data regarding the important parameters were input into adaptive neural-fuzzy networks (ANFIS) to predict erosion rates. The asymmetric factor (Af), hypsometric integral (Hi), and basin shape (BS) indicate that most of the sub-basins are tectonically active. The results of the PCA revealed that the most important parameters affecting erosion were Af, Pf, Lf, Rf, Vf, Pb, Ab, LC, Lb, Dd, and the geological unit. The ANFIS method showed that among the soil erosion prediction models, the FCM hybrid model had the highest accuracy. It is concluded that morphometric features can be used to predict the erosion processes in the basin.

Diagenesis and Thermal Maturity of the Cogollo Group rocks in the ANH-CR-Montecarlo-1X well, Cesar-Ranchería Basin, Colombia

In ANH-CR-Montecarlo-1X well located in the southern sector of the Cesar-Ranchería basin, Colombia, rocks of the middle Cretaceous outcrop, which have been defined as belonging to the Cogollo Group. The present study concerns with the diagenetic evolution and thermal maturity of this geological unit, integrating petrographic techniques (thin section microscopy and scanning electron microscopy), geochemistry (total organic carbon and pyrolysis rock-eval) and basic petrophysics, to establish the thermal maturity and the potential of rocks as reservoirs of conventional and unconventional hydrocarbons. The results of petrographic and diagenetic analysis revealed that the rocks compositionally correspond to quartz sandstones and graywackes and carbonate rocks to mudstones and wackestones; which were affected by diagenetic processes such as compaction, mineral neoformations distinguishing minerals from the group of clays that cover the grains of the framework, and other types of precipitates of cements such as silica, ferrous and non-ferrous carbonate, some of these present partial and/or total dissolution, for which secondary porosity is recognized, also metasomatisms, where processes of chloritization and illitization of the argillaceous matrix are observed, alteration of feldspars to ferrous and non-ferrous carbonate, which affects the porosity and permeability of the rock; and recrystallization from micrite to sparite and carbonate precipitation in calcareous rocks. The study also showed that the rocks were more affected by compaction than precipitation of the different cements. The research contributes to the understanding of the impact of diagenetic processes on porosity, as well as their spatial and temporal distribution, providing diagenetic paragenesis for both siliciclastic and carbonatic rocks. When we classifying siliciclastic rocks as potential reservoir rocks, low potential results were obtained as conventional reservoirs but has good potential as non-conventional reservoirs (tight sandstones), this respect to porosity and permeability data. The geochemical studies in the calcareous rocks exhibited low to good content of total organic carbon, overmaturity state and a low generation potential with type III and IV kerogens.

FÍSICO-QUÍMICA DE ÁGUAS E GEOQUÍMICA DE SEDIMENTOS EM SUSPENSÃO DE RECURSOS HÍDRICOS SUPERFICIAIS DO MUNICÍPIO DE BELÉM, ESTADO DO PARÁ

The municipality of Belém is installed on low ground under a rich and immense system of surface waters that converge for the most part directly into the Pará River system, Marajó Bay, northern fathom of the Amazon River and then the Atlantic Ocean. The Guamá river (estuary) and Guajará bay stand out, bathing its western, north and northeast portions, and numerous tidal channels, as well as several streams converge on the former, as well as several swamps and temporary wetlands. The main urban nucleus, the city of Belém, was installed and continues to do so, along the tidal and igarapé channels, modifying its courses, and polluting them brutally, either by solid waste or by domestic effluents of all kinds without any treatment, in addition to industrial contributions, becoming more serious as the city moves forward in horizontal and vertical buildings. The tides partially assist in this cleaning, by carrying a large part of these pollutants daily to the Guamá River, from this one to the Guajará Bay and then Marajó and Atlantic. Beautiful beaches in the north and northeast of the municipality (Outeiro, Mosqueiro, Farol, Ariramba, Carananduba, Paraíso and Baía do Sol) attract thousands of visitors, which further contribute to general pollution. Although several surveys have already been carried out to assess these impacts and its dilution, it was decided to try a new attack, emphasizing the Tucunduba stream and its drainage in the Guamá river, the Guajará bay on its margin of strong industrial-port impact and then the beaches of the Baía do Sol. Water and solid sediment in suspension (suspended) were collected in three different periods, considering the two tidal cycles, in eight seasons. Measurements of the main physical parameters were made in loco. Next, cations and anions in the waters analyzed, mineralogical identification and chemistry of the suspensates, in addition to micromorphological analyzes were carried out. The results show that the Guamá river and Guajará bay can be still classified as unpolluted natural waters, similar to the white waters of the Amazon region. Tucunduba and the waters of the Baía do Sol, mainly those restricted (swamps and manholes) are strongly altered by human occupation. Cations and anions, as well as microplankton from the suspension sediments, also allow identify the seasonal interference of oceanic interference during the dry season. The suspension materials of these rivers are dominated by quartz, kaolinite, partly muscovite / illite, demonstrating a strong relationship with the sediments of the margins, gullies and flood plains, and also of the Barreiras Formation, Neogene in age, the geological unit that serves as a substrate for the lands of Belém municipality. However, for a more informed assessment, a systematic and much more comprehensive study is recommended from the chemical, biological, mineralogical point of view and still under strong seasonal and tidal cycle controls, preferably for a continuous decade.