Switcher-HNet: A switchable hierarchical network for tree species classification from forest stand to individual tree tasks

<b>Switcher-HNet Project &amp; Demo</b><br>This <b>project</b> contains code for training, inference, and visualization of tree species classification models using the TreeSatAI and<b> </b>Hierarchical Individual Tree (HIT). Detailed instructions and function annotations are included in the code.<br>The <b>demo</b><b> </b>is available in Switcher_HNet_Demo.mp4<br><b>Hierarchical Individual Tree </b><b>(HIT) </b><b>Dataset</b><br>Area: Maoer_mountain_HSI_CHM_Field_data<br>The <b>HIT</b><b><i> </i></b><b>Dataset</b><b><i> </i></b><i>(</i><i>Maoer Mountain area</i><i>)</i> is a <b>multi-source</b> ecological dataset collected in the Maoer Mountain region, a biodiversity-rich area located in Harbin, <b>Northeast of China</b>.<br>This dataset supports research in forest ecology, species distribution modeling, remote sensing, and biodiversity conservation. It integrates high-resolution <b>hyperspectral imagery (HSI)</b>, <b>canopy height models (CHMs)</b>, and <b>ground-validated field data</b> to enable detailed tree species identification and forest structure analysis.<br>The HSI is characterized by a spatial resolution of approximately 0.2 meters per pixel, georeferenced to the WGS84 geographic coordinate system. It covers a spectral range of 387.8 to 1025.5 nm, distributed across 150 contiguous bands with an average spectral bandwidth of 4.28 nm.The CHMs are a single-band raster dataset aligned with the HSI, encoded in 32-bit floating-point format. It has a ground sampling distance of 0.250 × 0.250 meters and is georeferenced to a projected coordinate system based on the WGS84 datum.<br>The field data include the primary tree species of Northeast China, such as <i>Pinus koraiensis</i> and a variety of broadleaf species.