Markov Chain Modelling for Short-Term NDVI Time Series Forecasting (original) (raw)
Related papers
Applying Markov Chains for NDVI Time Series Forecasting of Latvian Regions
2015
Time series of earth observation based estimates of vegetation inform about variations in vegetation at the scale of Latvia. A vegetation index is an indicator that describes the amount of chlorophyll (the green mass) and shows the relative density and health of vegetation. NDVI index is an important variable for vegetation forecasting and management of various problems, such as climate change monitoring, energy usage monitoring, managing the consumption of natural resources, agricultural productivity monitoring, drought monitoring and forest fire detection. In this paper, we make a one-step-ahead prediction of 7-daily time series of NDVI index using Markov chains. The choice of a Markov chain is due to the fact that a Markov chain is a sequence of random variables where each variable is located in some state. And a Markov chain contains probabilities of moving from one state to other.
Forecasting based on Markov chain modely
Bhartiya Krishi Anusandhan Patrika
In this paper, we try to forecast crop yield by the probability model based on Markov Chain theory, which overcomes some of the drawbacks of the regression model. Markov Chain models are not constrained by a parametric assumption and are robust against outliers and extreme values. Here, multiple order Markov chain were utilized.
A non-stationary NDVI time series modelling using triplet Markov chain
International Journal of Information and Decision Sciences, 2019
Nowadays, vegetation monitoring using remotely sensed data is an important far-reaching real-world issue. The main purpose of this study is to build a triplet Markov chain (TMC) to model and analyse vegetation dynamics on large-scales using non-stationary normalised difference vegetation index (NDVI) time series. TMC is a generalisation of hidden Markov models (HMMs), which have been widely used to represent satellite time series images but which they proved to be inefficient for non-stationary data. The TMC model proposed in this paper overcomes this limit by adding an auxiliary process which allows modelling non-stationarity. In order to assess the performance of the proposed model, experimentation is carried out using moderate resolution imaging spectroradiometer (MODIS) NDVI time series of the northwestern region of Tunisia. The TMC model is compared to standard HMM and seasonal auto regressive integrated moving average model (SARIMA) and proved to achieve the best performance with an overall accuracy prediction rate of 92.8% and a kappa coefficient of 0.885.
International Journal of Remote Sensing, 2019
Building accurate relationships between vegetation amount and climatic variables is helpful in understanding and informing sustainable environmental management. The common approach in this regard is to develop a generic, linear relationship or seasondependent relationships. Such approaches, however, fail to hold if data characteristics deviate from expected patterns. This study applied a regime-switching regression model, namely the Markovswitching (MS) approach, to predict time-series Normalized Difference Vegetation Index (NDVI). This was done using surface temperature, soil moisture and the interaction of surface temperature and soil moisture as regressors at monthly temporal resolution. Modelling was executed at the biome spatial (broad vegetation categories) scale. The results showed that the MS approach captured the non-linear dynamics in the data for each of the eight biomes considered in the study. The accuracy of the MS approach compared to non-switching modelling approach was evident in model comparison criteria including significance of parameter estimates, coefficient of determination (R 2), Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and log-likelihood as well as post-modelling diagnostics such as residual plots, autocorrelation function (ACF) and partial autocorrelation function (PACF) of residuals, and squared residuals. Overall, the study clearly demonstrates the superiority of MS modelling that captures non-linear relationships that may not be modelled using conventional non-switching modelling. Further studies are encouraged to test the approach at larger spatial scales.
A Forecast Model Applied to Monitor Crops Dynamics Using Vegetation Indices (NDVI)
Applied Sciences, 2021
Vegetation dynamics is very sensitive to environmental changes, particularly in arid zones where climate change is more prominent. Therefore, it is very important to investigate the response of this dynamics to those changes and understand its evolution according to different climatic factors. Remote sensing techniques provide an effective system to monitor vegetation dynamics on multiple scales using vegetation indices (VI), calculated from remote sensing reflectance measurements in the visible and infrared regions of the electromagnetic spectrum. In this study, we use the normalized difference vegetation index (NDVI), provided from the MOD13Q1 V006 at 250 m spatial resolution product derived from the MODIS sensor. NDVI is frequent in studies related to vegetation mapping, crop state indicator, biomass estimator, drought monitoring and evapotranspiration. In this paper, we use a combination of forecasts to perform time series models and predict NDVI time series derived from optical...
2020
Professor Dr. tech. sc. Vadim Romanuke Polish Naval Academy, Poland DECLARATION OF ACADEMIC INTEGRITY I hereby declare that the Doctoral Thesis submitted for the review to Riga Technical University for the promotion to the scientific degree of Doctor of Engineering Sciences is my own. I confirm that this Doctoral Thesis had not been submitted to any other university for the promotion to a scientific degree. Artūrs Stepčenko ……………………………. (signature) Date: ……………………… The Doctoral Thesis has been written in Latvian. It consists of Introduction; 5 chapters; Conclusion; 36 figures; 21 tables; 4 appendices; the total number of pages is 171, including appendices. The Bibliography contains 121 titles.
The Markov models are frequently proposed to quickly obtain forecasts of the weather "states" at some future time using information given by the current state. One of the applications of the Markov chain models is the daily precip-itation occurrence forecast. There is tested a Markov chain model with two states for the daily precipitation in summer and winter seasons of 1961-1990 at several stations in Romania. The states of the Markov chain are precipitation occurrence and precipitation non-occurrence, that is wet and respectively dry days. There are computed the sets of conditional (or transition) probabilities for first-order, second-order and third-order Markov chain. To find the most ap-propriate model order among the different orders of the Markov chains for the daily precipitation series, the Bayesian information criterion (BIC) was used.
2015
In this paper predictions of the normalized difference vegetation index (NDVI) are discussed. Time series of Earth observation based estimates of vegetation inform about changes in vegetation. NDVI is an important parameter for vegetation forecasting and management of various problems, such as climate change monitoring, energy usage monitoring, managing the consumption of natural resources, agricultural productivity monitoring, drought monitoring and forest fire detection. Artificial Neural Networks (ANN's) are computational models and universal approximators, which are widely used for nonlinear, non-stationary and dynamical process modeling and forecasting. A layer recurrent neural network (LRN) is used in this paper to make one-step-ahead prediction of the NDVI time series.
The Use of Markov Model in Continuous Time for Prediction of Rainfall for Crop Production
In a first order Markov process, if the state is known for any specific values of the time parameter, that information is sufficient to predict the next behavior of the process beyond that point. This principle was used to formulate a four-state model in continuous time to study the annual rainfall data with respect to the annual rainfall distribution for crop production in minna. It was observed that if it is low rainfall in a given year, it would take at most 25%,33% and 27% of the time to make a transition to moderate rainfall also well spread, high rainfall, and moderate rainfall but not well spread respectively in the far future. Thus given the rainfall in a year, it is possible to determine quantitatively the probability of finding rainfall in other states in the following year and in the long run. This is an important information that could assist the farmers to plan strategies for high crop production in the region.
2016
This study analyzed Landsat data to investigate the expansion of vegetation in the state of Selangor, Peninsular Malaysia, using the NDVI and Cellular Automate Markov Chain method. Two sets of Landsat data acquired in 2000 and 2015 were analyzed. The Vegetated areas in each Landsat scene were extracted from NDVI images. Then, the two image sets, 2000 and 2015, were input into Idrisi software where the Markov algorithm was used to predict the vegetation expansion for the year 2030. The results show that the vegetated areas increased by 45% between 2000 and 2015. Similarly, a 55% increase in vegetation for the next 15 years (2015 to 2030) was predicted. This study suggests the need for better planning and management to balance between vegetation and urban area expansion