Grass is one of the crucial elements in representing real nature scenes. Various methods have been proposed for grass simulation, for example, Boulanger and his colleagues render realistic grass in real-time with dynamic lighting, shadows and animations. Till now, few approaches have investigated the realistic simulation of withering grassland which is still a big challenge in computer graphics, due to the great complexity of both geometry and withering mechanism. In our work, a novel concept called Time-Varying Texels (TVT) is proposed to extend the static texel[Kajiya and Kay 1989] and make it time-serialized. In a grass TVT structure, time-dependent texels are arranged hierarchically in a Time-Space Partitioning (TSP) tree, so that the grass withering process can be efficiently approximated, with acceptable spatial and temporal errors. In this way we facilitate LOD rendering. Traditional texel structures could hardly undertake physical based calculation in each grass blade, so we introduce a point based structure (PBS) to increase the flexibility. Dynamic processes such as geometric deformation and material transformation can be achieved on PBS during the whole withering procedure. Additionally, by clustering the pre-computed TVT samples in low densities using a mingling algorithm, we obtain high-density grass TVT so as to significantly improve the efficiency of TVT generation.