{"id":"W4296107209","doi":"10.3390/e24091304","title":"Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features","year":2022,"lang":"en","type":"article","venue":"Entropy","topic":"Planetary Science and Exploration","field":"Physics and Astronomy","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Terrain; Mars Exploration Program; Traverse; Artificial intelligence; Support vector machine; Computer science; Exploration of Mars; Remote sensing; Random forest; Computer vision; Pattern recognition (psychology); Geology; Geodesy; Geography; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001892744,0.00006853203,0.00008495065,0.00005496483,0.0001286889,0.00002130285,0.0001077602,0.000009758373,0.0001310884],"category_scores_gemma":[0.000006693674,0.00006416522,0.00005649422,0.0001058063,0.00001509335,0.0001401328,0.00001314116,0.00006923178,0.000008969738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002208617,"about_ca_system_score_gemma":0.00004300536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003822587,"about_ca_topic_score_gemma":7.711898e-7,"domain_scores_codex":[0.9994101,0.0000444372,0.0001111562,0.0001570953,0.0001575784,0.0001196447],"domain_scores_gemma":[0.9996535,0.00008951101,0.0001088526,0.0001025909,0.00001907684,0.00002644527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004494129,0.0004251096,0.002199188,0.00001184897,0.00003688561,4.7557e-7,0.0005160428,0.02690665,0.8966767,0.03669916,0.02387717,0.01220139],"study_design_scores_gemma":[0.003634511,0.00114964,0.03686049,0.00001355921,0.00006947298,7.071616e-7,0.003491428,0.8218331,0.0879992,0.002346451,0.04213372,0.0004677297],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05560508,0.000002796919,0.9400648,0.001529475,0.0004189002,0.0004200338,0.0007610729,0.00002206694,0.001175753],"genre_scores_gemma":[0.984072,1.009142e-7,0.01377515,0.0001549368,0.0001325751,0.00005939374,0.001617292,0.000005887184,0.0001826992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9284669,"threshold_uncertainty_score":0.2616582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02015913915763555,"score_gpt":0.2969112544251851,"score_spread":0.2767521152675495,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}