In Enlightengeo/GeoscienceBC_2019-008: Enlighten Geoscience BC 2019-008 Induced Seismicity Statistical Study Code

Geoscience BC Study Code - Machine Learning Wrapper

library(geosciencebc2019008)
run_date = Sys.Date() %>% str_replace_all(., "-", "_")
knitr::opts_chunk$set(eval = FALSE)

Load prepared data

This chunk loads our prepared data (see prepare_data.Rmd)

saf_wells_sf <- read_rds('../output/bcogc_saf_well_data.rds')
geologic_input_data = FALSE

Classification

aux_cols <- c(
  "unique_surv_id", "wa_num", "ground_elevtn",
  "mean_easting", "mean_northing", "on_prod_date"
  )

class_comp_feats = c(
  "calc_total_fluid_m3", "mean_rate_m3_min", "mean_proppant_per_stage_t",
  "proppant_cat", "horiz_wells_in_5km", "min_midpoint_dist",
  "calc_completed_length_m"
  )

class_geo_feats = c(
  "paleozoic_structure_mss", "geothermal_gradient_degc_km", "shmin_grasby",
  "distance_listric_faults_berger_m", "distance_normal_faults_berger_m"
  )

targets <- c("seismogenic", "max_mag")

ml_df <- saf_wells_sf %>%
  st_drop_geometry() %>% 
  dplyr::select(
    all_of(aux_cols), all_of(class_comp_feats), all_of(class_geo_feats), all_of(targets)) %>%
  dplyr::mutate_if(is.logical, as.numeric) %>%
  dplyr::filter(
    shmin_grasby > 0,
    !is.na(mean_proppant_per_stage_t),
    min_midpoint_dist > 0) %>%
  dplyr::mutate(seismogenic = as.factor(seismogenic))

# impute non-causal features
ml_df = impute(ml_df, cols = list(
  mean_rate_m3_min = imputeMean()
  ))$data

# one hot encode categorical variables
ml_df <- createDummyFeatures(
  ml_df, target = "seismogenic", cols = c("proppant_cat")) %>% 
  removeConstantFeatures(.) %>%
  dplyr::select(-proppant_cat.ceramic, -proppant_cat.resin.coated, -proppant_cat.sand)

write_csv(ml_df, paste0("../output/","final_bcgoc_mldf_class.csv"))
write_rds(ml_df, paste0("../output/","final_bcogc_mldf_class.rds"))

Regression

regr_comp_feats  = c(
  "calc_total_fluid_m3", "calc_total_proppant_t", "calc_completed_length_m",
  "n_stages", "min_midpoint_dist", "mean_rate_m3_min"
  )

regr_geo_feats = c(
  "pressure_depth_ratio_kpa_m", "top_montney_structure_mss", "third_order_residual_m",
  "geothermal_gradient_degc_km", "distance_listric_faults_berger_m",
  "distance_normal_faults_berger_m"
  )

targets <- c("seismogenic", "max_mag")

ml_df <- saf_wells_sf %>%
  st_drop_geometry() %>% 
  dplyr::select(
    all_of(aux_cols), all_of(regr_comp_feats), all_of(regr_geo_feats), all_of(targets)) %>%
  dplyr::mutate_if(is.logical, as.numeric) %>%
  dplyr::filter(min_midpoint_dist > 0) %>%
  dplyr::mutate(seismogenic = as.factor(seismogenic))

# impute non-causal features
ml_df = impute(ml_df, cols = list(
  mean_rate_m3_min = imputeMean()
  ))$data

write_csv(ml_df, paste0("../output/","final_bcgoc_mldf_regr.csv"))
write_rds(ml_df, paste0("../output/","final_bcogc_mldf_regr.rds"))

Enlightengeo/GeoscienceBC_2019-008 documentation built on Feb. 4, 2021, 12:43 p.m.