Delineation of Cocoa Agroforests Using Multiseason Sentinel-1 SAR Images: A Low Grey Level Range Reduces Uncertainties in GLCM Texture-Based Mapping

Abstract

Delineating the cropping area of cocoa agroforests is a major challenge in quantifying the contribution of land use expansion to tropical deforestation. Discriminating cocoa agroforests from tropical transition forests using multispectral optical images is difficult due to the similarity of the spectral characteristics of their canopies. Moreover, the frequent cloud cover in the tropics greatly impedes optical sensors. This study evaluated the potential of multiseason Sentinel-1 C-band synthetic aperture radar (SAR) imagery to discriminate cocoa agroforests from transition forests in a heterogeneous landscape in central Cameroon. We used an ensemble classifier, Random Forest (RF), to average the SAR image texture features of a grey level co-occurrence matrix (GLCM) across seasons. We then compared the classification performance with results from RapidEye optical data. Moreover, we assessed the performance of GLCM texture feature extraction at four different grey levels of quantization: 32 bits, 8 bits, 6 bits, and 4 bits. The classification’s overall accuracy (OA) from texture-based maps outperformed that from an optical image. The highest OA (88.8%) was recorded at the 6 bits grey level. This quantization level, in comparison to the initial 32 bits in the SAR images, reduced the class prediction error by 2.9%. The texture-based classification achieved an acceptable accuracy and revealed that cocoa agroforests have considerably fragmented the remnant transition forest patches. The Shannon entropy (H) or uncertainty provided a reliable validation of the class predictions and enabled inferences about discriminating inherently heterogeneous vegetation categories.

Argan Tree (Argania spinosa (L.) Skeels) Mapping Based on Multisensor Fusion of Satellite Imagery in Essaouira Province, Morocco

“…However, the integration of texture features (scenario combining texture, VH, and VH/VV) increased the discrimination of the argan tree (PA = 46:27% instead of PA = 29:80% and PA = 32:16% for the scenarios VV, VH, VH/VV, and VV, VH, respectively). This confirms the contribution of texture features in the improvement of the tree species classification accuracy using SAR data[6,8,68,71].…”

“…GLCM is a probability measure of two gray levels separated by a given distance occurring in the same orientation. According to the literature [70][71][72][73], the most common and popular GLCM texture features used for tree type discrimination are as follows: correlation, mean, and variance. These three texture measurements were calculated and used for the present study.…”

Monitoring and Mapping of Rice Cropping Pattern in Flooding Area in the Vietnamese Mekong Delta Using Sentinel-1A Data: A Case of An Giang Province

“…Orthorectification and terrain correction were done using SRTM 30-m DEM data. The biggest speckle noise was often found in SAR data [62,63]. We used the Enhanced Lee filter to reduce SAR speckle noise since Enhanced Lee has more advantages compared to other filters.…”

Detecting cocoa plantations in Côte d’Ivoire and Ghana and their implications on protected areas

“…Combining such features with a Random Forest (RF) classification model ( Breiman, 1999 ), farms have successfully been used to map cocoa on a small scale. Numbisi et al (2019) noted that the level of confusion between cocoa agroforests and transition forests was low compared to other classes. This indicates that optimising the image texture information improved the classification and helped to identify vegetation classes with a highly heterogeneous canopy.…”

“…The combination of optical and radar data derivatives have proven to be useful in detecting shrub crops grown under forest canopies ( De Alban et al, 2018 ). Texture analysis can also be used to differentiate cocoa farms from rubber, oil palm and other tree types ( Descals et al, 2019 , Numbisi et al, 2019 ). Combining such features with a Random Forest (RF) classification model ( Breiman, 1999 ), farms have successfully been used to map cocoa on a small scale.…”