Planted Forest Fire Burn Area and Impact Assessment Using Sentinel-2: Case Study of the University of Ilorin Teak Plantation

Abstract

Abstract This paper presents a comprehensive assessment of the locations, extent and the impact of forest fire in University of Ilorin Teak Plantation using pre- and post-fire Sentinel-2 level 1C products. First, the pre-fire image was classified into three classes: vegetation area, bare soil and water body, using supervised classification (Maximum Likelihood method) to distinguish between vegetation and non-vegetation areas. Then, from the post-fire image, the burn areas were detected and extracted using Normalized Burnt Ratio. With the burn area polygon, impact of the fire on the planted forest was determined by isolating the vegetation class within the classified map so estimating the number of teak trees affected through extrapolation of the burn area and the tree spacing grid of 3m. The classification result shows that vegetation land cover type accounted for about 419.7 ha (66 %) of the total area while bare soil and water body take 204.3 ha (32 %) and 12.9 ha (2 %), respectively. Also, the resulting classified map produced overall classification accuracy of 95 %. Impact assessment result reveals that a total number of 49156 tree stands were affected by the fire within burnt area of 54.8 ha (8.6%). Analysis of the estimation success rate using one of the burn areas as validation site yielded approximation in excess of 3% with 17621 counted and 18222 estimated. Planted forest management and planning has many phases; so, it is necessary to understand the current and future condition of what is being manage. The fire burn map derived from this study will assist the University teak plantation management team update its current management strategy to protect it from continuous exposure to fire. From fire management perspective, the list of planning activities that require future assessments include pruning preferences, replanting, commercial thinning, spacing of planted trees, and perimeter buffering.