Forecasting Land use/Land Cover Change for 2030 AD | Prediction Land use/Landcover Change

                                                                          INTRODUCTION

Land use planning is a process of making informed decisions about the future use of lands, waters, and other resources Land use plans use the best available information in a transparent and accountable manner to achieve a defined vision and goals for the planning area. Land-use planning can play an essential role in guiding land use and land cover changes (LULCC) over time, has the potential to minimize soil quality decline and can enhance climate change resilience, However, to be effective, it must be defined and implemented fairly, involving relevant stakeholders, such as public and private land-owners The study of LULCC is relevant to better understand several phenomena occurring in the territory and quantify their spatiotemporal environmental impacts, particularly on water and soil resources. The planned development is essential for sustainable development and thus the optimal use of available resources. Since resources are limited it becomes necessary to use the resources wisely Urban areas which are characterized by high population density are required to develop as per proper plans which are known as development plans or master plans. These plans provide both theoretical and spatial information which will govern the growth of the towns and cities. Land use planning forms most crucial part in these plans and is shown in the land use map of such plans It is done utilizing color coding, i.e., by assigning a specific color for a particular activity on the map On maps which cover a large area, the predominant land use is shown, and colors are given as per single-level hierarchy, no further details of activity are shown under the given land use For example, only the residential area will be shown and the possible additional information about the government housing, embassy areas, plotted housing etc.

A land use plan has many different functions, which may include:

Ø  Developing maps and policy direction

Ø  Identifying what land use activities are allowed, where, and under what conditions

Ø  Setting out rules for the conservation, development, and use of land, water, and resources

Ø  Prohibiting or allowing land use activities, such as oil and gas development, mining, commercial tourism, or forestry.

Ø  Creating conservation zones to protect ecological values or traditional and cultural use
Ø  Providing direction or guidance for land and water use activities, such as bulk water
Ø  Removal, waste management, transportation, and infrastructure development
Establishing regional zones and broad criteria to help evaluate and screen project proposals as part of regulatory permitting processes

   OBJECTIVES

The main objective of the study is to prepare land use plan of Omsatiya rural municipality, and the sub objective are as follows:

Ø  To Study the existing land use pattern, Changes etc.

Ø  To Collect Demographic Data

Ø  To Collect Geographical Data

Ø  To analyses the past and present land use for future land use forecasting.

Ø  To Prepare GIS-Based Map and Geo Database.

   SCOPE OF WORK

The scope of the work is to carry out the land use plan of Omsatiya Rural Municipality. The work has to be carried out either in high-resolution satellite images acquired from the latest Google Earth platform or Freely Available Remote Sensing Data.

A thorough analytical approach should be adopted to assess the feasibility of the project. Enlist roads, drainage, existing residential, educational and other institutions, social infrastructures (hospitals, training institutions, NGOs etc.) and other infrastructures of the project area.

Ø  Land-use Change Spatial analysis and Forecasting.

Ø  Preparation of Complete GIS-Based Map of Municipality Level.

Major Driving Factors for the Land use Change Pattern

National Highways

There are major highways such as Siddhartha Highway and Hulaki Highway passes through the rural municipality. These highways are the one of major factor to change the future land use.

These two national highways offer many development opportunities in the rural municipality such as:

  Settlement and Market Centers

The land topography is plain which is suitable for the development of settlement in the rural municipality The existing road network is almost developed in the settlement and need to be upgraded.

The core market center of the municipality is Thutipipla Bazar along the Siddhartha Highway. Omsatiya R-Municipality lies within Strategic Postal Highway, which indicates the potential of transit point of export/import business. This rural municipality is near to the Siddharthanagar, Butwal, Bhairawa and India Boarder. It has created a great possibility to be a transit Area.

The local existing markets and settlement and their potential development has been listed below Table below.

S.N.	Name of Settlements and Markets	Ward No	Types	Potential Areas	Road Access
1	Thutepiple	1	Major Settlement/ Major Markets	Expansion Settlement / Market/Business/Trade	Highway (H10)
2	Padasari	2	Major Settlement/ Major Markets	Expansion Settlement	Highway (H10)
3	Tarkulaha	3	Major Settlement	Expansion Settlement	49DR019
4	Farsatikhar	3	Major Settlement	Expansion Settlement/Local Markets	Urban Road
5	Balapur to Darkhasawaa	4	Major Settlement/Makets	Expansion Settlement/ Market/Business/Trade	Hulaki Highway Corridor
6	Gaurigaun	5	Main Market	Religious tourism	49DR020
7	Pathkhauli	5	Major Settlement	Expansion Settlement	49DR020
8	Chotki Ramnagar	6	Major Settlement	Expansion Settlement /Local Market	Urban Road
9	Narainapur	6	Major Settlement	Local Market	49DR021
10	Bindrapur	6	Major Settlement	Expansion Settlement/ Local Market	49DR022
11	Jamwani	6	Major Settlement	Expansion Settlement/ Local Market	49DR022

    

  

The municipal executive office of Omsatiya R-municipality is located at Farsatikhar ward no 3. The R-Municipal office is situated almost mid part of the rural municipality which has been connected via good urban rode network. This may offer a high possibility to develop as an institutional zone in the rural municipality

Industry

The rural municipality can develop a large number of small to medium industries such as food processing, dairy processing, agro-processing, and others which may serve the local people and other municipalities, and the whole District.

 Agriculture/Forestry and Its Processing

With the suitable topography and climate available in the R-municipality, agricultural production especially the vegetables, cash crops, herbal products, livestock and fruits can be given higher priority and the processing of agricultural products is a potential for the economic development of the city.

Tourism

As this rural municipality is easily accessible with roadway, Siddhartha Highway and Postal Highway (National Highway). The Eco-tourism and religious tourism is a great opportunity in the rural municipality The large land is covered by fish farming which makes agriculture fields with ponds in the rural municipality. This may offer building eco-home stay along the r-municipal area. The Omsatiya temple is one of the renowned temples in the vicinity which may attract numerous religious tourists in the rural municipality. The mela, sports programs, festivals, cultures, terai community are specific features that are the baseline in the tourism development which helps in trade and business.

Selection and Preparation of the Drivers

Driver selection and preparation was one of the major tasks performed in this study. Initially, a desk study using; journals articles, reports, and related documents was done to retrieve the responsible driving factors for LULC changes in the study area. Then after all drivers were analyzed to examine their impact on LULC changes over the study period. Further, to accomplished the main aim of this study driving factors for the year 2010 was selected, categorized and prepared on the following same literature The main reason for only selecting the drivers of year 2010 was due to scope of study and model requirement which is explained details in further next step (Inputs) The procedure adopted for selection of drivers for year 2010 is illustrated in the figure below.

land use Forecast Drivers Map

land use Forecast Drivers Map

     Inputs

Inputs are the initial parameters to be inserted for modeling and predicting via the MOLUSCE plugin. In this study model needs to predict for year 2030, thus it was first calibrated and validated by simulating the LULC of 2021 For this purpose, LULC raster datasets of 2000 and 2010 were inserted in plugin interface as initial and final year respectively. to precisely simulate LULC of 2021.

  Evaluation of Correlation

The ‘Evaluating Correlation’ was used to assess the correlation between the input driving factors for year 2010 Assessment of correlation is vital before transition potential modeling because if highly correlated drivers will be there during modeling more computational power is required for the CA-ANN model Slope was excluded in this study due to its high correlation with DEM, else other were carried as it is.

Transition Potential Modelling

This step mainly produced the transition potential maps which will act as the main basis for the further stimulation of LULC 2021 by CA-ANN model. Various types of operational parameters should maintain the transition potential modeling. It includes six parameters; Samples (Random), Neighborhood, Learning rate, Momentum, Maximum Iterations, Learning on the literature and necessity of study During transition modelling, 5000 randomly selected pixels were divided into two sets; 80 % for training and 20% for validation. Similarly, 10 hidden layer was selected for precise prediction of the LULC classes for year 2021. Moreover, momentum (0.05), learning rate (0.1), and neighborhood size (3*3) are the other selected parameters that connect all the layers (Input, Hidden, and Output layer) of the CA-ANN model.

     CA-ANN Simulation for Year 2021

CA-ANN model simulates the LULC for year 2012 based on the four essential elements i.e. CA (C,n,K,R); where C are represented by pixels, n is represented by the number of classes, K represents the Moore neighborhood of size, and R represents the transition potential maps (TPMs). During this step, CA-ANN model recognizes for each pixel of the year 2000 and 2010 with the highest TPMs values generated through transition potential modeling. This step and transition potential modeling are interconnected with each other and follow black box approach for simulating the LULC classes. After completing the simulation of the LULC for 2021 a raster map was generated which shows the spatial distribution of the LULC over the study area.

Validation

Validation was done to assess the potential of the CA-ANN model to predict LULC for the year 2030 in an allocated study area. During this step actual LULC raster map for the year 2021 (acquired) and simulated LULC raster map for the year 2021 (generate) were inserted in the ‘Validation’ tab of the plugin. The two major outputs of this step were; % of correctness and kappa (overall). The outcomes generated from this step are detailed depicted in the results and findings section. This step was iteratively done until desirable accuracy was achieved.

     Simulated LULC for Year 2030

After acquiring the desired accuracy in the validation step the prediction of the LULC for year 2030 was initiated. At first, n value was changed into 2 in the Input tab of the plugin. Since, for n= 1,2,3…. will predict for 2021, 2030, when input was given as 2000 for initial and 2010as final year respectively. Then after, assuming the same value of correctness of the CAANN model with same inputs, drivers, ANN operational value model was operated to predict for year 2030. The generated LULC for year 2032 is detail depicted in the result and findings section

Land use Change (2000 - 2021)	Area Change (Sq.KM)
Built Up-Built-up	1.581761
Built Up-Cultivation Area	0.000323
Built Up-Forest	0.000005
Built Up-Sand	0.000437
Built Up-Water Bodies	0.00866
Cultivation-Built-up	3.15313
Cultivation-Cultivation Area	41.2221
Cultivation-Forest	0.128729
Cultivation-Sand	0.052566
Cultivation-Water Bodies	0.091953
Forest-Built-up	0.038536
Forest-Cultivation Area	0.805607
Forest-Forest	0.415081
Forest-Sand	0.012946
Forest-Water Bodies	0.022298
Sand-Built-up	0.000312
Sand-Cultivation Area	0.311105
Sand-Forest	0.08088
Sand-Sand	0.037523
Sand-Water Bodies	0.049638
Water Bodies-Built-up	0.000484
Water Bodies-Cultivation Area	0.335385
Water Bodies-Forest	0.057327
Water Bodies-Sand	0.078963
Water Bodies-Water Bodies	0.092616
Grand Total	48.578364

Landuse Change (2021 - 2030)	Area_ Change (Sq.KM)
Builtup - Built Up	4.568271
Builtup - Cultivation Land	0.205956
Cultivation Area - Built Up	1.680875
Cultivation Area - Cultivation Land	40.99367
Forest - Built Up	0.019948
Forest - Cultivation Land	0.662075
Water Bodies - Built Up	0.001201
Water Bodies - Cultivation Land	0.017269
Water Bodies - Water Bodies	0.429128
Grand Total	48.578393