{"id":"W4386211640","doi":"10.36227/techrxiv.24032043","title":"Multi-modal Contrastive Learning for Crop Classification Using Sentinel2 and Planetscope","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Bundesministerium für Umwelt, Naturschutz, nukleare Sicherheit und Verbraucherschutz; Deutsche Forschungsgemeinschaft","keywords":"Modal; Computer science; Artificial intelligence; Generalization; Machine learning; Representation (politics); Pattern recognition (psychology); Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001634524,0.0009608956,0.0004809278,0.0007754168,0.000281525,0.0005213242,0.001105637,0.0008399368,0.0009042529],"category_scores_gemma":[0.002142774,0.0002406582,0.0009622006,0.0005524216,0.000418726,0.001114005,0.0007627695,0.0009714674,0.0005987518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006020069,"about_ca_system_score_gemma":0.0004729295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007023352,"about_ca_topic_score_gemma":0.01148033,"domain_scores_codex":[0.9992908,0.0002206725,0.00002312565,0.0002421294,0.0001412249,0.00008190236],"domain_scores_gemma":[0.999281,0.0002332676,0.00006636589,0.0002042952,0.0001760699,0.00003903608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007941526,0.00104359,0.0245388,0.0002343356,0.000457277,0.0002680528,0.0002235103,0.5559121,0.03410194,0.002350169,0.01827034,0.3618058],"study_design_scores_gemma":[0.00001197034,0.00003991799,0.002716008,0.000005009925,0.000009116415,0.00002719269,0.00002198644,0.99089,0.004472411,0.0008937407,0.0009015127,0.00001112407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5185462,0.0008432305,0.4616395,0.0006633783,0.0002678883,0.0002112665,0.0033771,0.009108292,0.005343175],"genre_scores_gemma":[0.8111598,0.0001454735,0.1763874,0.0002616741,0.00008222475,0.0001165149,0.008536709,0.0002433028,0.003066873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007023352,"threshold_uncertainty_score":0.01396495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1330225283337999,"score_gpt":0.2960570335393348,"score_spread":0.1630345052055349,"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."}}