Nomadic Herding: A Sustainable Way of Life

Join us as we explore the world of nomadic herding, from the traditional knowledge and skills used by nomadic herders to the economic and environmental benefits of this unique way of life. Discover how nomadic herding can be a sustainable and valuable part of the modern world.

Like so many else, I’ve been experimenting with ChatbotGPT from I’m completely blown away by the possibilities and the level of content that it manages to create.

To test it, I asked it to give me some catchy title suggestions for a blog post about nomadic pastoralism. One of the suggestions was “Nomadic Herding: A Sustainable Way of Life”!

So here it goes; I think it was pretty good but see for yourself:

write a 800 words blog post titled “Nomadic Herding: A Sustainable Way of Life”

Nomadic herding is a traditional way of raising livestock that involves moving from one place to another in search of pasture and water. This way of life has been practised for thousands of years and continues to thrive in many parts of the world. As a result, nomadic herders have a deep connection to the land and a wealth of traditional knowledge and skills to manage their animals and sustain their way of life.

But what makes nomadic herding a sustainable way of life? To answer this question, it’s essential to understand the unique characteristics of nomadic herding and how it can benefit the environment and local communities.

One of the critical characteristics of nomadic herding is the use of large, mobile herds of animals. This allows nomadic herders to move their animals to different areas in search of fresh pasture and water, and it will enable the land to recover after the animals have grazed. In addition, this type of mobility helps to prevent overgrazing and soil erosion and helps maintain the land’s health.

In addition, nomadic herders have a deep understanding of the land and its resources, using this knowledge to manage their animals and grazing patterns. This allows them to avoid damaging sensitive areas, such as wetlands and riverbanks, and to maximize the productivity of the land. Nomadic herders also use various traditional herding techniques, such as rotational grazing, to manage their animals and maximize the benefits of grazing.

Another critical aspect of nomadic herding is its role in conserving biodiversity. Nomadic herders often move their animals to different areas in search of pasture and water, which can help preserve their animals’ genetic diversity. In addition, nomadic herding can help to maintain the diversity of plant and animal species in a given area. This is because nomadic herders often graze their animals on land unsuitable for agriculture, which can help preserve natural habitats and ecosystems.

Nomadic herding also provides significant economic and social benefits to local communities. Nomadic herders provide food, fibre, and other products essential to many rural areas’ economies. In addition, nomadic herding can help create jobs and support local businesses. Nomadic herders also play a vital role in maintaining cultural traditions and identity, and they can help preserve a given area’s cultural heritage.

Despite the many benefits of nomadic herding, some challenges must be addressed to ensure its sustainability. One of the biggest challenges is the loss of pasture and water due to the expansion of agriculture, mining, and other forms of development. This can make it difficult for nomadic herders to find suitable grazing land for their animals, leading to conflict with other land users. In addition, nomadic herders must deal with the challenges of climate change, which can lead to changes in precipitation patterns and other impacts on the land.

To address these challenges, it is essential to support nomadic herding and to recognize its value as a sustainable way of life. This can be done through various measures, such as providing access to education, healthcare, and other services for nomadic herders.

This took me 5 minutes (or rather, it took 5 minutes to come up with the query to ChatbotGTP)… After that, I used Grammarly to freshen up some of the writing!

The ramifications are mind-blowing!!


Using Python to summarize articles

Earlier this year I got an article published in Acta Borealia.

The paper, The Sami cooperative herding group: the siida system from past to present, is open access.

I usually publish a short summary on this blog, but recently I’ve been learning to analyze text using Python so I thought I should try to leverage Python to help me summarize my own paper.

The result? Have a look (I’ve only removed citations and reorganized the sentences for flow):


The Sami – both pastoralists and hunters – in Norway had a larger unit than the family, i.e., the siida.


Historically, it has been characterized as a relatively small group based on kinship.

The siida could refer to both the territory, its resources and the people that use it.

The core institutions are the baiki (household) and the siida (band).

Names of siidas were, in other words, local.

Moreover, it was informally led by a wealthy and skillful person whose authority was primarily related to herding.

One of these groups’ critical aspects is that they are dynamic: composition and size change according to the season, and members are free to join and leave groups as they see fit.


Only two herders reported to have changed summer and winter siida since 2000.

Furthermore, while the siida continues to be family-based, leadership is becoming more formal.

Nevertheless, decision-making continues to be influenced by concerns of equality.


The code is shown below. Lacks a bit in comments, but should work for documents. I’ve load the text used from a docx file.


import numpy as np
import os
import sys
import nltk
from nltk.corpus import stopwords
import re
import textacy # have installed spacy==3.0 and textacy==0.11
import textacy.preprocessing as tprep
import docx
import networkx as nx
from sklearn.feature_extraction.text import TfidfVectorizer
import nltk
import os
import warnings

stop_words = nltk.corpus.stopwords.words('english')
wtk = nltk.tokenize.RegexpTokenizer(r'\w+')
wnl = nltk.stem.wordnet.WordNetLemmatizer()

Loading file

doc = docx.Document('your_filename.docx')

Functions for processing and summarizing text

def extract_text_doc(doc):
    paras = [p.text for p in doc.paragraphs if p.text]
    revised_paras = [p for p in paras if len(p.split('.')) >1]
    text = " ".join(revised_paras)
    return text

def normalize_document(paper):
    Tokenize ++
    paper = paper.lower()
    paper_tokens = [token.strip() for token in wtk.tokenize(paper)]
    paper_tokens = [wnl.lemmatize(token) for token in paper_tokens if not token.isnumeric()]
    paper_tokens = [token for token in paper_tokens if len(token) >2]
    paper_tokens = [token for token in paper_tokens if token not in stop_words]

    doc = ' '.join(paper_tokens)
    return doc

def normalize(text):
    Normalizes text, string as input, returns normalized string
    text = tprep.normalize.hyphenated_words(text)
    text = tprep.normalize.quotation_marks(text)
    text = tprep.normalize.unicode(text)
    text = tprep.remove.accents(text)
    return text

def text_rank_summarizer(norm_sentences, original_sentences, num_sent):
    if len(sentences) < num_sent:
        num_sent -=1

    tv_p = TfidfVectorizer(min_df=1, max_df=1, ngram_range=(1,1), use_idf=True)
    dt_matrix = tv_p.fit_transform(norm_sentences)
    dt_matrix = dt_matrix.toarray()

    vocab = tv_p.get_feature_names()
    td_matrix = dt_matrix.T

    similarity_matrix = np.matmul(dt_matrix, dt_matrix.T)

    similarity_graph = nx.from_numpy_array(similarity_matrix)

    scores = nx.pagerank(similarity_graph)

    ranked_sentences = sorted(((score,index) for index, score in scores.items()))

    top_sentence_indices = [ranked_sentences[index][1] for index in range(num_sent)]
    summary = "\n".join(np.array(original_sentences)[top_sentence_indices])
    return summary

Processing text

normalize_corpus = np.vectorize(normalize_document)
text = extract_text_doc(doc)
text1 = normalize(text)
sentences = nltk.sent_tokenize(text1)
norm_sentences = normalize_corpus(sentences)
summary = text_rank_summarizer(norm_sentences, sentences, 10)

Historically, it has been characterized as a relatively small group based on kinship.
Moreover, it was informally led by a wealthy and skilful person whose authority was primarily related to herding.
Only two herders reported to have changed summer and winter siida since 2000.
Furthermore, while the siida continues to be family-based, leadership is becoming more formal.
Nevertheless, decision-making continues to be influenced by concerns of equality.
One of these groups' critical aspects is that they are dynamic: composition and size changes according to the season, and members are free to join and leave groups as they see fit.
Lowie (1945) writes that the Sami – both pastoralists and hunters – in Norway had a larger unit than the family, i.e., the siida.
Names of siidas were, in other words, local.
The siida could refer to both the territory, its resources and the people that use it (see also Riseth 2000, 120).
The core institutions are the baiki (household) and the siida (band).

For more options and better ways of summarizing text, check out with its many summarizer classes. For example, TextRankSummarizer is similar (but way better) than the approach taken here.

But similarly, it conceptualizes the relationship between sentences as a graph: each sentence is considered as vertex and each vertex is linked to the other vertex. But, rather than using PageRank from networkx for similarity, it uses Jaccard Similarity.

Density or climate: Is that the question?

A recent paper argues that climate is more important than density in the reindeer husbandry in Norway. Using the same analysis, I find that reindeer density is essential: In high-density environments, average varit (1.5-year-old bucks) carcass weight is 8 kg lower, and calf carcass weight is 4 kg lower compared to low-density environments.

A recent paper, ‘Productivity beyond density: A critique of management models for reindeer pastoralism in Norway’, published in Pastoralism: Research, Policy and Practice sets out to investigate the validity of the premise that there is a strong relationship between density and carcass weights in the reindeer husbandry in Norway.

In short, the paper aims to challenge the official view of overstocking and reframe reindeer herding in terms of non-equilibrium ecology.

Their focus of attack is the Røros model which, according to the authors, hinges on

“… classic ecological equilibrium models where there is a clear unequivocal relationship between animal densities, production, and carcass weights”

p. 15

As such the article fits nicely in a growing trend: rather than investigating problems currently facing pastoralists, the main point is to establish systems as non-equilibrium, and thus all issues are assumed resolved, or at least externally caused (for an excellent example from the reindeer husbandry in Norway, check out ‘Conceptualising resilience in Norwegian Sámi reindeer pastoralism‘).

In another paper, some of the same authors have, for example, argued that reindeer herding in Norway is better characterised as a non-equilibrium system

“…where herbivore populations fluctuate randomly according to external influences, [and] the concepts of carrying capacity and overgrazing have no discernible meaning”.

Misreading the Arctic landscape: A political ecology of reindeer, carrying capacities, and overstocking in Finnmark, Norway’, p. 223

Productivity beyond density’ goes at least further in attempting to quantify the relative importance of non-equilibrium factors (such as climate) and equilibrium factors (such as density).

While the paper is well-written and exciting, I find it a bit strange that in the only quantitative analysis they present the sole focus is on statistically significant effects of precipitation and temperature for the carcass weights of reindeer:

Source: Table 1 in publication.

While the analysis shows indeed that climate factors (precipitation: all the daily observation in the stated period and growing degree days [GDD]) are significant, the discussion of the table completely fails to address two critical factors:

They never discuss whether the variables measuring climate is correlated or not (as they are monthly based, it wouldn’t be a huge surprise if they are).

High or even moderate, collinearity is problematic when effects are weak (as the climate effect sizes indicate). If collinearity is ignored, it is possible to end up with a statistical analysis where nothing is significant, but were dropping one predictor may make others significant, or even change the sign of estimated parameters.

The point is technical; it would be interesting to see how these potential problems were accounted for.

Concerning effect size, the most substantial effect by far is that of density: -0.16 kg for calves and -0.32 kg for varit (1.5-year-old bucks).

In effect, this has a considerable impact on the carcass weights in high-density vs low-density environments

Keep in mind that they do not provide information concerning variable transformation, so I take it for granted that the intercept represents average carcass weights when every other variable is at zero. I also take for granted that all variables are continuous. Moreover, not all of the data was in the supplemental material so I couldn’t re-analyse the data properly.

In short, at density 0 average calf carcass weight is 18.52 kg and average varit carcass weight is 25.34 kg.

The paper does not indicate the range of density utilised in this analysis, but Fig. 5 presents the range for mainland districts (which are the same districts used in table) to be from 0 to 25.

Disregarding the climate parameters (since there are no interactions and the range of the climate parameters are not presented) density has a significant effect in high-density environments:

Calves: 18.52 – 0.16 X 25 = 14.52 kg

Varit: 25.34 – 0.32 X 25 = 17.34 kg

In short, the model in Table 1 predicts that the difference in varit carcass weight between a low-density environment and a high-density environment is 8 kg. For calf carcass weight, the model predicts a difference of 4 kg.

While I fully agree with the authors that an over-emphasis on density and herd size is too simplistic when modelling pastoral production, it is bizarre that the above is not communicated at all.

Part of the problem, I think, stems from the simplified representation of non-equilibrium ecology. Concerning Africa and Asia, for example, they write “…a wholesale paradigm shift from equilibrium to non-equilibrium modelling took place from the early 1990s” (p. 9).

This is in fact, only partially true.

In the chapter ‘Why are there so many animals? Cattle population dynamics in the communal areas of Zimbabwe’, Ian Scoones, for example, investigated factors affecting herd growth among Zimbabwean pastoralists.

He mainly focused on periodic events such as droughts (a density-independent factor) and more persistent factors such as herd size (a density-dependent factor)

In other words, he investigated the degree to which density-dependent and density-independent factors explained herd size fluctuations (data for 60 years).

In short, he found:

  • In years with high precipitation, the population of cattle approaches a ceiling, which he terms the carrying capacity. As density increases, the birth rate drops, and mortality rates increases (although they never reach equilibrium and the cattle population never reaches its theoretical maximum).
  • The cattle population never reaches a maximum because stochastic events such as droughts occur and kill off large parts. Noteworthy, the number of animals killed by these events was more substantial than what can be predicted from density-dependent factors alone.

In the long term, it thus looks like non-equilibrium factors have the most significant impacts on cattle populations. Still, equilibrium factors are essential in years without stochastic climatic effects and when the population is high.

Scoones’ investigation show what seems now to be forgotten:

It is unlikely that any system is characterised by either equilibrium or non-equilibrium factors alone, but rather that they both operate on a continuum.

This supports the predominant ecological perspective that at high population sizes, herbivores are sensitive to a combination of density-dependent and -independent factors, which has been shown for reindeer in Norway.

As I argued in the paper ‘Climate Change, Risk Management and the End of Nomadic Pastoralism’.

“To understand the effects of climate change on nomadic pastoralists, it is thus necessary to move beyond the simplistic dichotomy of characterising pastoral system as equilibrial (density dependence: livestock and pastures are regulated by grazing pressure) or non-equilibrial (density independence: livestock and pastures are limited by external factors such as climate) and look at the interplay between density dependent and density independent factors”

p. 131