Satellite images provide an accurate, continuous, and synoptic view of seamless global extent. Within the fields of remote sensing and image processing, land surface change detection (CD) has been amongst the most discussed topics. This article reviews advances in bitemporal and multitemporal two-dimensional CD with a focus on multispectral images. In addition, it reviews some CD techniques used for synthetic aperture radar (SAR). The importance of data selection and preprocessing for CD provides a starting point for the discussion. CD techniques are, then, grouped based on the change analysis products they can generate to assist users in identifying suitable procedures for their applications. The discussion allows users to estimate the resources needed for analysis and interpretation, while selecting the most suitable technique for generating the desired information such as binary changes, direction or magnitude of changes, “from-to” information of changes, probability of changes, temporal pattern, and prediction of changes. The review shows that essential and innovative improvements are being made in analytical processes for multispectral images. Advantages, limitations, challenges, and opportunities are identified for understanding the context of improvements, and this will guide the future development of bitemporal and multitemporal CD methods and techniques for understanding land cover dynamics.
1 January 2013 in Journal of the Saudi Society of Agricultural Sciences
Rice is one of the important agricultural products in Indonesia. The production has been fully supported by infrastructure including research and development as well as government regulations in pricing. Its vulnerability to climate change requires adaptation strategies on irrigation, biotechnology and selection of alternative crops. The primary goal of this paper was to evaluate the historical perspective of the dynamics of rice production, technologies particularly in seed inventions, labour in farming and consumption of rice from 1961 to 2009 in conjunction with land capability. The study of historical rice production could be a benefit for future agricultural planning in Indonesia
Agricultural drought monitoring is paramount in order to maintain food security in Indonesia, particularly in Subang and Karawang as the national rice production centers. In this paper, satellite-borne remote sensing data are tested for monitoring drought extent in about 184.486ha of both regencies. Vegetation Health Index (VHI), a vegetative drought indices based on remote sensing data, is studied in this case using long term sequence of 2000, 2005, 2010, and 2015 dry season Landsat data. VHI collates overall vegetation health, which in turn suitable to indicate agricultural drought extent. It measures either moisture vegetation/vegetation condition (VCI) or thermal condition of vegetation (TCI). Both indices were derived from Normalized Difference Vegetation Index (NDVI) and land surface temperature (LST) data respectively. The results revealed that VHI decreased more than 50 percent, from 30.86 in 2000 to 14.66 in 2015. This figure indicated drought extent intensified in research area, from mild drought to severe drought. The severity was mainly triggered by the rising LST from 27°C in 2000 to 40°C in 2015. In addition, there was a decreasing tendency of NDVI values in recent years, leading agricultural fields more susceptible to drought
21 March 2017 in International Journal of Remote Sensing
This study evaluates four commonly used forms of synthetic aperture radar (SAR) data for land-cover classification in tropical rural areas. The backscatter coefficient of linearly polarized L-band SAR was compared to two distinctive feature sets derived from Eigen-based and model-based decompositions. The performance of six classifiers available in Orfeo Toolbox (OTB), that is, Bayes, artificial neural networks (ANNs), Support Vector Machine (SVM), decision trees, Random Forests (RFs), and gradient boosting trees (GBTs), was investigated to distinguish five and seven land-cover classes, with particular attention given to several types of woody vegetation: forest, mixed garden, rubber, oil palm, and tea plantations. Classifiers reacted differently to ingested forms of SAR data, and careless use of data input yielded a negative impact. The results showed that SVM provided the highest overall accuracy although the performance was not significantly better than the others. Tuning the parameters, however, significantly improved the accuracy of ANN and SVM, while RF and GBT did not respond well. Responses of two SVM parameters (cost and kernel type) fluctuated somewhat, which required further attention. ANN accuracy was improved when the number of neurons in the hidden layer was set between 10 and 12. We found that accuracy imbalance existed between designated land-cover classes, especially in woody vegetation. Imbalance can partially be reduced by tuning specific classifiers. We showed that classifier tuning can lead to significantly improved accuracy, especially for classes having medium or low accuracies. This research also demonstrated that freely available toolkits such as OTB and QGIS can be beneficial for mapping activities in developing countries, achieving a reasonable accuracy if the classification parameters are tuned properly.
This research aims to detect subtle changes by combining binary change analysis, the Iteratively Reweighted Multivariate Alteration Detection (IRMAD), over dual polarimetric Advanced Land Observing Satellite (ALOS) backscatter with augmented data for post-classification change analysis. The accuracy of change detection was iteratively evaluated based on thresholds composed of mean and a range constant of standard deviation. Four datasets were examined for post-classification change analysis including the dual polarimetric backscatter as the benchmark and its augmented data with indices, entropy alpha decomposition and selected texture features. Variable importance was then evaluated to build a best subset model employing seven classifiers, including Bagged Classification and Regression Tree (CAB), Extreme Learning Machine Neural Network (ENN), Bagged Multivariate Adaptive Regression Spline (MAB), Regularised Random Forest (RFG), Original Random Forest (RFO), Support Vector Machine (SVM), and Extreme Gradient Boosting Tree (XGB). The best accuracy was 98.8%, which resulted from thresholding MAD variate-2 with constants at 1.7. The highest improvement of classification accuracy was obtained by amending the grey level co-occurrence matrix (GLCM) texture. The identification of variable importance (VI) confirmed that selected GLCM textures (mean and variance of HH or HV) were equally superior, while the contribution of index and decomposition were negligible. The best model produced similar classification accuracy at about 90% for both years 2007 and 2010. Tree-based algorithms including RFO, RFG and XGB were more robust than SVM and ENN. Subtle changes indicated by binary change analysis were somewhat hidden in post-classification analysis. Reclassification by combining all important variables and adding five classes to include subtle changes assisted by Google Earth yielded an accuracy of 82%.
Information on land reserves is crucial and required to support agricultural development in relation to increased population pressure, food demand, and food security. This research aims to identify and evaluate idle abandoned land based on biophysical suitability, status of land concessions, and forest areas to determine potential land reserves for agricultural development to support food security in Indonesia. The results show that, at the national level, the area of suitable abandoned lands for agricultural extensification is 27.7 million ha, but most of these lands have concession permits and are located in forest areas, so 12.4 million ha are still available, with the largest area being in dry land. The identification of abandoned land by employing satellite imagery in 54 districts resulted in a smaller acreage compared to abandoned land being mapped formally at 1:250,000. After considering land ownership and forest status, both sources resulted in similar areas at a scale of 1:50,000 and 1:250,000, i.e., 6.1 million ha and 6.0 million ha, respectively. It seems that land ownership and forest status adjusted the total acreage of identified land reserves at different map scales. An area of around 7.4 million ha will be required to meet food demand in 2045 by assuming constant consumption per capita. We found about 1.7 million ha as potential land reserves, most of which are in conversion or production forests areas. Converting forests or utilizing drylands could be potential alternatives to deal with the lack of land for food production. Moreover, due to limited wetlands, the use of reserve land in that agroecological zone should be in accordance with its designation, comply with the priority principles, and be supported by government regulations and policies, so that food security can be maintained until 2045.