{"id":"W3177036350","doi":"10.5194/isprs-annals-v-3-2021-257-2021","title":"A COMPARISON OF MACHINE LEARNING MODELS FOR SOIL SALINITY ESTIMATION USING MULTI-SPECTRAL EARTH OBSERVATION DATA","year":2021,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Environmental science; Soil salinity; Salinity; Soil science; Dryland salinity; Arid; Mean squared error; Earth observation; Remote sensing; Arable land; Hydrology (agriculture); Soil water; Satellite; Soil fertility; Geology; Mathematics; Statistics; Geography; Engineering; Soil biodiversity","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":[0.004532118,0.001151135,0.0009627219,0.001436088,0.0004014594,0.0009229538,0.001042876,0.001180777,0.0009684935],"category_scores_gemma":[0.005598944,0.0003606172,0.001171795,0.0008899304,0.000228184,0.001049025,0.0005273484,0.0009443046,0.0004504407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008534449,"about_ca_system_score_gemma":0.0008466347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01510414,"about_ca_topic_score_gemma":0.006817136,"domain_scores_codex":[0.9990042,0.0005134902,0.00008348702,0.0001864304,0.0001384416,0.00007410725],"domain_scores_gemma":[0.996556,0.00237392,0.0001865528,0.0001281093,0.0006877429,0.0000676767],"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":[0.0005085411,0.0003437737,0.01464557,0.0001454963,0.0003630077,0.00006585799,0.00005644409,0.8335901,0.001303438,0.0005739154,0.0009670075,0.1474369],"study_design_scores_gemma":[0.000003961672,0.00002884277,0.0009266178,0.000005205563,0.000009844285,0.000004127785,0.000006303269,0.9986985,0.0001641198,0.00009736311,0.00005124001,0.000003884586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5562798,0.003370841,0.4332843,0.0008156883,0.0003419166,0.0002163567,0.0005174844,0.00200482,0.003168778],"genre_scores_gemma":[0.9483937,0.0004605787,0.04934513,0.0001167926,0.00004881046,0.000139604,0.0005095891,0.00003532968,0.0009504385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01510414,"threshold_uncertainty_score":0.03003246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2530764229251078,"score_gpt":0.3818490249472078,"score_spread":0.1287726020221,"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."}}