Land Suitability Mapping (LSM) is a procedure to group specific land area in the form of its suitability based on the particular type of use. It provides geospatial information about crop cultivation in which they are well suited and also play vital role in addressing modern-day situations such as feeding more than 9 billion people, coping with climatic variations and ensuring sustainable productions. Despite this known drawbacks, an best alternative methods is necessary to decline mapping unit for land suitability for variety of crop production. The objective of this present review is to help farmers and academic research scholars in assessing land suitability in different agricultural areas for better yield prediction using geospatial techniques. Landscape and soil factors are especially important when coupling with Geographic Information Systems (GIS) and Remote Sensing (RS) using Machine Learning (ML) techniques. This provides a guide map and superior database for making decisions in substantial growth of crops in horticulture. Review findings are based on 79 research articles with time span of eight years (2014-2021), collected mainly on Web of Science database. The paper identifies better geospatial techniques involved in mapping land suitability levels from various agricultural crops.