A new method for remote-sensing land-use/land-cover (LULC) change detection is proposed to eliminate the effects of forest phenology on classification results. This method is insensitive to spectral changes caused by vegetation seasonality and uses an object-based approach to extract geostatistical features from bitemporal Landsat TM (Thematic Mapper) images. We first create image objects by multiresolution segmentation to extract geostatistical features (semivariogram parameters and indices) and spectral information (average values) from NDVI (normalized difference vegetation index), acquired in the wet and dry seasons, as input data to train a Support Vector Machine algorithm. We also used the image difference traditional change-detection method to validate the effectiveness of the proposed method. We used two classes: (1) LULC change class and (2) seasonal change class. Using the most geostatistical features, the change detection results are considerably improved compared with the spectral features and image differencing technique. The highest accuracy was achieved by the sill (σ² overall variability) semivariogram parameter (95%) and the AFM (area first lag–first maximum) semivariogram index (88.33%), which were not affected by vegetation seasonality. The results indicate that the geostatistical context makes possible the use of bitemporal NDVI images to address the challenge of accurately detecting LULC changes in Brazilian seasonal savannahs, disregarding changes caused by phenological differences, without using a dense time series of remote-sensing images. The challenge of extracting accurate semivariogram curves from objects of long and narrow shapes requires further study, along with the relationship between the scale of segmentation and image spatial resolution, including the type of change and the initial land-cover class.

In forested areas that experience strong seasonality and are undergoing rapid land cover conversion (e.g., Brazilian savannas), the accuracy of remote sensing change detection is affected by seasonal changes that are erroneously classified as having changed. To improve the quality and consistency of regionally important forest change maps, we aim to separate process related change (for example, spectral variability due to phenology) from changes related to deforestations or fires. Seasonal models are typically used to account for seasonality, but fitting a model is difficult when there are insufficient data points in the time series. In this research, we utilize remotely sensed data and related spectral trends and the spatial context at the object level to evaluate the performance of geostatistical features to reduce the impact of seasonality from the NDVI (Normalized Difference Vegetation Index) of Landsat time series. The study area is the São Romão municipality, totaling 2440 km², and is part of the Brazilian savannas biome. We first create image objects via multiresolution segmentation, basing the objects on the characteristics found in the first image (2003) of the 13-year time series. We intersected the objects with the NDVI images in order to extract semivariogram indices, the RVF (Ratio Variance—First lag) and AFM (Area First lag—First Maximum), and spectral information (average and standard deviation of NDVI values) to generate the time series from these features and to derive Spatio-Temporal Metrics (change and trend) to train a Random Forest (RF) algorithm. The NDVI spatial variability, captured by the AFM semivariogram index time series produced the best result, reaching 96.53% of the overall accuracy (OA) to separate no-change from forest change, while the greatest inter-class confusion occurred using the average of the NDVI values time series (OA = 63.72%). The spatial context approach we presented is a novel approach for the detection of forest change events that are subject to seasonality (and possible miss-classification of change) and mitigating the effects of forest phenology without the need for specific de-seasoning models.

Change detection methods are often incapable of accurately detecting changes within time series that are heavily influenced by seasonal variations. Techniques for de-seasoning time series or methods that apply the spatial context have been used to improve the results of change detection. However, few studies have explored Landsat’s shortwave infrared channel (SWIR 2) to discriminate between seasonal changes and land use/land cover changes (LULCC). Here, we explored the effectiveness of Operational Land Imager (OLI) spectral bands and vegetation indices for detecting deforestation in highly seasonal areas of Brazilian savannas. We adopted object-based image analysis (OBIA), applying a multidate segmentation to an OLI time series to generate input data for discrimination of deforestation from seasonal changes using the Random Forest (RF) algorithm. We found adequate separability between deforested objects and seasonal changes using SWIR 2. Using spectral indices computed from SWIR 2, the RF algorithm generated a change map with an overall accuracy of 88.3%. For deforestation, the producer’s accuracy was 88.0% and the user’s accuracy was 84.6%. The SWIR 2 channel as well as the mid-infrared burn index presented the highest importance among spectral variables computed by the RF average impurity decrease measure. Our results give support to further change detection studies regarding to suitable spectral channels and provided a useful foundation for savanna change detection using an object-based method applied to Landsat time series.