. . . . . . . . . . . "This article presents a pseudomultitask (PMT) segmentation neural network (PMTNet) for cropland mapping in\r\nmountainous regions using high-resolution remote sensing images.\r\nPMTNet extends BsiNet by introducing two key innovations: 1)\r\na pixel-level mask and edge features fusing module using distance features (MEF_D), and 2) a PMT module that replaces the\r\nconventional multibranch-task predictions. The MEF_D module\r\nleverages spatial attention guided by distance features as weighting\r\nindicators to effectively fuse mask and edge features at the pixel\r\nlevel, leading to improved boundary representation. The PMT\r\nmodule, serving as the core prediction component, consists of a\r\nsingle branch dedicated to mask prediction. The two auxiliary\r\ntasks—edge detection and distance mapping—are derived directly\r\nfrom the mask output using the Canny edge detecting algorithm\r\nand Euclidean distance transformation, respectively. The model\r\nwas trained and evaluated using cropland samples from Chongqing\r\nand Fenghuang, China, based on high-resolution remote sensing\r\nimages. Comparative experiments were conducted against two\r\nrepresentative multitask neural networks (BsiNet and SEANet) and\r\ntwo transformer-based semantic segmentation models (HRFormer\r\n+ OCR and LRFormer). The results demonstrated that PMTNet\r\nconsistently outperformed these baselines, achieving the highest\r\nscores across multiple metrics, including precision, recall, F1-\r\nscore, intersection over union, overall accuracy, and the Kappa\r\ncoefficient—all within a compact model size. Applicability analysis confirmed that PMTNet can effectively identify croplands\r\nof diverse types, shapes, and cultivation stages, as long as their\r\nboundaries in the images are visually distinguishable" . "A Pseudomultitask Neural Network Classification Model for Cropland Mapping in Mountainous Areas Using High-Resolution Remote Sensing Images" . . . "xzhou@mtech.edu" . "January 2026" . "2025" . . "Emily Regalado" . "2026-05-01T17:43:55.415Z"^^ . . . . . . . . . "RSA" . "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAxzr6UBGMW6c8tegz0babaledWUEQ0PLDE4tp7Iinbe2DZtAtY5JUptKYuStWDZx+QER4808P8dejNWRnBDzgthYJm/AyNSXflHSJhz2+NC+h7RylOLxbwLEQocmyKKiYxa2gT85m6ajVL2M6TnfG67nnK+K2f7iCGL6wYXRITD1q+7+5SWqBdDXIV921W4IKWaD2GJk+NRBoOqQhbsrk8Tn5XsNd7DMYVHk47oMDGbeBnrOIoRPsbBgAcoCsxxhiB9yN6Lf8EUbnlXVEDzJuZk048L1BDZL+6nkA8btTQGP2ijUFWA7rTrod3LjUDQWLZS95njjl867dtmv/znYkzwIDAQAB" . "d9Kesh3LxI5756VpO1MYDoBq39Fmf3qnh2ruP/pJgvepMoAbcmL7zhb86Bo1FJhXmkNRJ+ye27r/jrS2jChe5j1e9HtNDTuAoBMPLrVXYYNrNeCZV4LuC2hi+XI1AxyZSS03XqQDKvsI1iaVBHiStC+El4ZxFKAeFOoBGBkSI/cIAgAJQetXG8qzPbzzmYlxzYIUUNu4sXHe8yj9xxvmP8Did21bq2cGE2hykfJP4Zb1pUjHjnxpGGQojAoV69fIa0bgWhNnZxkwDMXAgxL4Hc/IXdZtGIaQUvOHfFHbi/kVmOt4rFXN2/7XgiWgNaFTCfsFSxs51kJyKv/iKVc3vg==" . . .