 we have developed two new methods for improving laser-based forest inventories. The first method uses the difference in elevations between the surfaces of trees detected by the first and last laser pulses to separate them. This method has been tested in Evo, Finland, and it has been found to improve the accuracy of detecting individual trees by up to 6%. Additionally, the second method combines the use of traditional point height metrics with individual tree-based features to produce more accurate estimates of forest variables such as volume and diameter. This combination of features has been shown to increase the accuracy of these measurements by up to 30% depending on the variable being measured. These two methods are both applicable to any type of forest inventory and could provide significant improvements in accuracy and cost savings. This article was authored by Hennu Haipa, Miko Vastaranta, Marcus Holopainen, and others.