{"id":"W4386211936","doi":"10.36227/techrxiv.24032043.v1","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; Generalization; Artificial intelligence; Machine learning; Representation (politics); Scale (ratio); Pattern recognition (psychology); Remote sensing; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001544899,0.0009357486,0.0004660784,0.000775633,0.0002804619,0.0004975826,0.00110452,0.0008003153,0.0008439666],"category_scores_gemma":[0.002084086,0.0002301211,0.0009304562,0.0005636799,0.0004370042,0.001076306,0.0007758585,0.0009185742,0.0005402685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005475344,"about_ca_system_score_gemma":0.0004494963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00584792,"about_ca_topic_score_gemma":0.01005919,"domain_scores_codex":[0.9993456,0.00018333,0.00002213022,0.0002363294,0.0001371145,0.00007541297],"domain_scores_gemma":[0.9993001,0.0002273671,0.00006783121,0.0001911475,0.0001768618,0.00003671566],"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":[0.0007784927,0.0009439806,0.02622527,0.0002514055,0.0004196702,0.0002269116,0.0002176096,0.5898193,0.03461281,0.002243886,0.01493032,0.3293305],"study_design_scores_gemma":[0.0000118088,0.00004246267,0.002886212,0.000005245363,0.000009749281,0.0000278063,0.00002097865,0.9903564,0.004833045,0.0009038221,0.0008912067,0.0000112271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5483017,0.0007582262,0.4337969,0.0005557956,0.0002217327,0.0001953787,0.003072764,0.007769347,0.005328153],"genre_scores_gemma":[0.8336711,0.00013283,0.1552033,0.0002224726,0.0000718413,0.0001137053,0.007552578,0.0002168495,0.002815317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00584792,"threshold_uncertainty_score":0.01162779,"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."}}