A multispectral feature framework for predicting soybean high temperature resistance grades based on masked autoencoding and supervised contrastive learning with dual-branch pretraining一种基于掩码自编码和监督对比学习的双分支预训练的多光谱特征框架,用于预测大豆高温抗性等级Engineering Applications of Artificial IntelligenceIF82025-12-090PRE